# AgentGid > AgentGid helps you discover, compare and track AI agents with public data: package downloads, editor installs, GitHub activity, releases, pricing and reliability, refreshed daily. Data is refreshed daily from public sources (npm, PyPI, GitHub, VS Code Marketplace, Homebrew, Wikipedia, Hacker News and vendor status pages). ## Rankings and data - [AI Agent Rankings: Downloads, Growth and Releases, Updated Daily](https://agentgid.com/) - [AI Agent Categories](https://agentgid.com/categories/) - [AI Agent News: Releases, Launches and Usage Jumps, Live](https://agentgid.com/news/) - [Are AI Agents Down? Live Status of Claude Code, Codex, Cursor and More](https://agentgid.com/status/) - [AI Agent Use Cases: 67 Real Examples, Recipes and Showcases](https://agentgid.com/use-cases/) - [AI Agent Release Tracker: What Changed This Week](https://agentgid.com/releases/) - [Fastest Growing AI Agents: Top Gainers and Losers](https://agentgid.com/movers/) - [Coding Agent Pull Requests on GitHub: Volume and Merge Rates](https://agentgid.com/github-activity/) - [Methodology](https://agentgid.com/methodology/) - [Data sources](https://agentgid.com/data-sources/) ## Agents - [OpenAI Codex](https://agentgid.com/agents/openai-codex/): OpenAI's coding agent, offered as an open-source terminal CLI, an IDE extension, a desktop app and a cloud agent that works on repositories. Users sign in with a ChatGPT account or use an OpenAI API key. - [OpenClaw](https://agentgid.com/agents/openclaw/): Open-source personal AI assistant that runs on the user's own machine as a gateway and works through chat apps such as WhatsApp, Telegram, Slack, Discord and iMessage, with a skills system and swappable model plugins. It also ships native apps for macOS, iOS, Android and Windows. - [Claude Code](https://agentgid.com/agents/claude-code/): Anthropic's agentic coding tool that reads a codebase, edits files and runs commands from the terminal, with VS Code and JetBrains integrations plus desktop, web and mobile access. It runs Claude models through a Claude subscription, an Anthropic Console API key or supported third-party cloud providers. - [LangChain](https://agentgid.com/agents/langchain/): A framework for building LLM applications and agents from composable parts: model integrations, tools, retrievers and prebuilt agent abstractions. Available for Python and JavaScript. - [n8n](https://agentgid.com/agents/n8n/): A workflow automation platform with a visual editor, several hundred integrations and native AI agent nodes. It can be self-hosted or used as a cloud service. - [Pi](https://agentgid.com/agents/pi/): Minimal, extensible open-source coding agent harness with interactive TUI, print/JSON, RPC and SDK modes, created by Mario Zechner and now maintained by Earendil Inc. It supports 15+ model providers through API keys or OAuth and is customized with TypeScript extensions, skills and packages. - [OpenCode](https://agentgid.com/agents/opencode/): Open-source coding agent from Anomaly (the team behind SST) that runs as a terminal UI, desktop app or IDE extension and connects to 75+ model providers, including local models and existing ChatGPT or GitHub Copilot logins. - [LiteLLM](https://agentgid.com/agents/litellm/): An AI gateway and Python SDK that calls 100+ model APIs through one OpenAI-style interface, with spend tracking, budgets, rate limits, fallbacks, guardrails and logging. - [Cursor](https://agentgid.com/agents/cursor/): AI coding editor and agent platform with a desktop app, a CLI, web and mobile agents, and cloud agents that run tasks in remote environments. It offers models from OpenAI, Anthropic, Google, SpaceXAI (Grok) and Meta alongside its own Composer models. - [GitHub Copilot](https://agentgid.com/agents/github-copilot/): AI coding assistant from GitHub offering completions, chat and agent mode in IDEs, a terminal CLI, a desktop app and a cloud agent that works on assigned tasks in the background and opens pull requests. Models from several providers can be selected. - [LangGraph](https://agentgid.com/agents/langgraph/): A low-level orchestration framework for building stateful agents as graphs, with durable execution, persistence and human-in-the-loop steps. Available for Python and JavaScript. - [AI SDK](https://agentgid.com/agents/vercel-ai-sdk/): Vercel's TypeScript toolkit for building AI applications and agents, with one API across model providers and UI helpers for streaming. - [Unity CLI MCP server](https://agentgid.com/agents/unity-cli-mcp/): The Unity CLI includes an MCP server, started with `unity mcp` and built on the Unity Pipeline package, that lets external coding agents such as Claude Code, Cursor, VS Code and Windsurf control a running Unity Editor locally. It replaces the deprecated MCP server in the com.unity.ai.assistant package, is marked experimental, and works alongside Unity's skills-only plugin for Claude Code, Codex and Grok. - [Unity in-editor AI assistant](https://agentgid.com/agents/unity-ai-assistant/): Unity's agentic assistant runs inside the Unity 6 Editor, inspects the scene, GameObjects and components, carries out Editor actions and checks that the changes work; it also includes asset generators that an organization can switch off. Unity is retiring the "Unity AI" brand name, the tools are in beta, and they are meant for Unity developers. - [Firecrawl](https://agentgid.com/agents/firecrawl/): Turns websites into clean Markdown or structured data for AI agents: scrape, crawl, map and search the web through one API. - [Langfuse](https://agentgid.com/agents/langfuse/): An open-source platform for tracing, evaluating and debugging LLM apps and agents: every model and tool call with its cost and latency, prompt management, datasets and evaluations. - [Strands Agents](https://agentgid.com/agents/strands-agents/): An open-source SDK from AWS for building and controlling agents in Python and TypeScript. - [Dify](https://agentgid.com/agents/dify/): An open-source platform for building agentic workflows, retrieval pipelines and LLM applications with a visual builder. Available self-hosted or as a cloud service. - [Claude Agent SDK](https://agentgid.com/agents/claude-agent-sdk/): Anthropic's SDK that exposes the agent loop, tools and context management behind Claude Code, for building custom agents in Python and TypeScript. - [DeepSeek Harness](https://agentgid.com/agents/deepseek-harness/): An agent harness from DeepSeek in which every capability is a plugin. Its agent reads and edits workspace files, runs commands, delegates work and keeps a plan, and it runs as a desktop app, a browser UI or the dsh command-line tool. - [Browser Use](https://agentgid.com/agents/browser-use/): Open-source Python library and hosted cloud that let LLM agents control a real browser to complete web tasks, with a CLI, a cloud API for hosted agents and browsers, and its own BU2 model option. - [Lovable](https://agentgid.com/agents/lovable/): Stockholm-based prompt-to-app builder that generates full-stack web apps with a built-in cloud backend and Git sync, and can be used from iOS/Android apps, Slack and Telegram. It grew out of the GPT Engineer App. - [E2B](https://agentgid.com/agents/e2b/): Secure cloud sandboxes where AI agents run code, use a filesystem and terminal, and browse, isolated from your own machines. - [ElevenLabs Agents](https://agentgid.com/agents/elevenlabs-agents/): ElevenLabs' conversational agent platform (formerly Conversational AI) for building and deploying voice and chat agents across web, mobile, telephony and messaging channels. - [Replit Agent](https://agentgid.com/agents/replit-agent/): AI agent inside Replit's browser-based platform that builds, tests and deploys full-stack web and mobile apps from natural-language prompts. It runs in Free, Power and Max agent modes and includes hosting, databases and a design product. - [Zed](https://agentgid.com/agents/zed/): High-performance open-source code editor written in Rust, with multiplayer editing, an agent panel, edit predictions and support for external agents through the Agent Client Protocol. Version 1.0 shipped in April 2026. - [Stagehand](https://agentgid.com/agents/stagehand/): Open-source SDK from Browserbase for building browser agents that mix natural-language actions (act, extract, observe, agent) with code, available in TypeScript, Python and Go and runnable locally or on Browserbase cloud browsers. - [Mastra](https://agentgid.com/agents/mastra/): A TypeScript framework for building agents and AI workflows, with memory, evals, retrieval and observability built in. - [Deep Agents](https://agentgid.com/agents/deepagents/): A batteries-included agent harness built on LangGraph, with planning, a virtual file system and sub-agents for long-running tasks. - [Rasa](https://agentgid.com/agents/rasa/): Framework and platform for building voice and chat assistants that can be self-hosted: the open-source Rasa framework (Apache-2.0) and the open-core Rasa Pro / Rasa Platform. A free Developer Edition license covers one bot with capped monthly conversations. - [Gemini CLI](https://agentgid.com/agents/gemini-cli/): Google's open-source terminal agent that brings Gemini models to the command line for code editing, shell commands and MCP tools. Since 2026-06-18 it no longer serves free, Google AI Pro/Ultra or Google One users, who were moved to Antigravity CLI. - [CopilotKit](https://agentgid.com/agents/copilotkit/): A full-stack SDK for agent-native application frontends with chat UI, generative UI, shared state and human-in-the-loop for React, Angular, Vue, React Native and chat channels; the team maintains the AG-UI protocol. - [Cloudflare Agents SDK](https://agentgid.com/agents/cloudflare-agents/): Cloudflare's SDK for building stateful agents that run on Workers and Durable Objects. - [Hermes Agent](https://agentgid.com/agents/hermes-agent/): Open-source self-improving agent from Nous Research that keeps persistent memory, creates and refines skills from experience, runs scheduled automations, and works from a terminal interface or messaging apps such as Telegram, Discord, Slack and WhatsApp. It can run locally or on Docker, SSH, Modal and Daytona backends, and has a desktop app. - [Oh My Pi](https://agentgid.com/agents/oh-my-pi/): Open-source terminal coding agent (`omp`), a variant of the Pi coding agent from Stencil Labs, with a native Rust core, IDE-style tooling and Windows-native support. - [DSPy](https://agentgid.com/agents/dspy/): A framework for programming language models with declarative modules and optimizers instead of hand-written prompts. - [Composio](https://agentgid.com/agents/composio/): Connects AI agents to 1,000+ apps and APIs with managed authentication, tool search and a sandboxed workbench, so agents can take actions in tools like GitHub, Slack and Gmail. - [OpenAI Agents SDK](https://agentgid.com/agents/openai-agents-sdk/): OpenAI's lightweight framework for multi-agent workflows, with handoffs, guardrails, sessions and tracing. Available for Python and TypeScript. - [MCP for Blender (formerly BlenderMCP)](https://agentgid.com/agents/mcp-for-blender/): MCP for Blender is an open-source add-on and MCP server that lets LLM clients such as Claude, Codex, Cursor and VS Code control Blender, editing scenes and pulling assets from Poly Haven, Sketchfab and Poly Pizza. It can also generate 3D models through Hyper3D Rodin, Hunyuan3D or Tripo, and it is an independent project not affiliated with the Blender Foundation. - [Junie](https://agentgid.com/agents/junie/): JetBrains' LLM-agnostic coding agent, available inside JetBrains IDEs, as a terminal CLI, in JetBrains Air and in CI through GitHub and GitLab integrations. It supports bring-your-own-key models and a free Junie Lite tier. - [Warp](https://agentgid.com/agents/warp/): Rust-based terminal that has grown into an agentic development environment, with a built-in coding agent, a standalone Agent CLI and the Oz cloud-agent platform. Its client was open-sourced in April 2026. - [Crawl4AI](https://agentgid.com/agents/crawl4ai/): An open-source web crawler and scraper that turns any website into clean, LLM-ready Markdown, run on your own machine or through Crawl4AI Cloud. - [Agno](https://agentgid.com/agents/agno/): A Python framework and runtime for building multi-agent systems with memory, knowledge and tools. Formerly known as Phidata. - [Cline](https://agentgid.com/agents/cline/): Open-source autonomous coding agent for VS Code (and JetBrains) that also ships a CLI, a desktop app and an SDK. It works with many model providers through the user's own keys, Cline's usage-billed provider or the ClinePass subscription. - [Devin](https://agentgid.com/agents/devin/): Autonomous AI software engineer from Cognition that runs in cloud VMs, takes work from Slack, Teams, Linear, Jira or an API, and delivers pull requests. Devin Desktop and the Devin CLI act as local companions to the cloud agent. - [CrewAI](https://agentgid.com/agents/crewai/): A Python framework for orchestrating teams of role-playing agents (crews) and event-driven workflows (flows). - [Chatwoot Captain](https://agentgid.com/agents/chatwoot-captain/): Chatwoot is an open-source omnichannel support desk (live chat, email, WhatsApp and social inboxes) and Captain is its AI agent that answers from help-center content, PDFs and websites. The core is MIT-licensed with an enterprise directory under a separate license, and it can be self-hosted or used as a hosted plan. - [Manus](https://agentgid.com/agents/manus/): General-purpose autonomous agent that plans and runs multi-step tasks in a cloud sandbox, such as research, slides, websites and data analysis, with web, desktop, mobile and browser-extension clients. Manus 2.0, announced in September 2026, added a new agent harness, dedicated cloud computers and a desktop studio. - [LiveKit Agents](https://agentgid.com/agents/livekit-agents/): A framework for building realtime voice and video AI agents on LiveKit's WebRTC infrastructure. - [TradingAgents](https://agentgid.com/agents/tradingagents/): A research framework in which several model agents act as analysts, researchers, a trader and risk managers and debate a market analysis; the project states it is for research only and not financial advice. - [Retell AI](https://agentgid.com/agents/retell-ai/): Platform for building, testing, deploying and monitoring AI voice and chat agents, with built-in telephony, prompt and flow builders, tool calling and analytics. - [Flowise](https://agentgid.com/agents/flowise/): A visual builder for AI agents and LLM workflows, distributed as an npm package and a Docker image. - [TesterArmy e2e](https://agentgid.com/agents/tester-army-e2e/): A TypeScript SDK, runner and CLI for end-to-end tests of web and mobile apps in which agent steps carry out natural-language tasks in real browsers, simulators or emulators; agent steps are recorded on the first run and replayed without model calls until the app changes. - [mini-SWE-agent](https://agentgid.com/agents/mini-swe-agent/): Open-source software-engineering agents from Princeton and Stanford researchers: SWE-agent (2024) and its roughly 100-line successor mini-SWE-agent, which uses only bash and works with any model through LiteLLM and similar routers. The SWE-agent README says development effort has moved to mini-SWE-agent. - [Vapi](https://agentgid.com/agents/vapi/): Developer platform and API for building, testing and deploying voice AI agents for phone and web calls, combining third-party speech-to-text, language model and text-to-speech providers. - [OpenHands](https://agentgid.com/agents/openhands/): Open-source AI software-development agent platform (formerly OpenDevin) with a local web GUI, a terminal UI/CLI, a hosted cloud and an SDK. It is model-agnostic and can use the user's own keys. - [Orca](https://agentgid.com/agents/orca/): Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime. - [Qualified Piper](https://agentgid.com/agents/qualified-piper/): Piper is an AI sales development agent that engages website visitors and inbound leads through chat, voice, video and email, qualifies them and books meetings, with Salesforce integration. - [eve](https://agentgid.com/agents/eve/): A filesystem-first framework for durable backend AI agents in which instructions, tools, skills, channels and schedules live as files in conventional locations; created by Vercel and in beta. - [Amazon Q Developer](https://agentgid.com/agents/amazon-q-developer/): AWS's AI coding assistant (the successor to Amazon CodeWhisperer) offered as IDE plugins, a command-line agent and chat in the AWS console, Slack and Teams. AWS is retiring the IDE plugins in favor of Kiro. - [Context7](https://agentgid.com/agents/context7/): Gives coding agents up-to-date, version-specific documentation and code examples for libraries, through an MCP server or API, instead of relying on what the model memorised. - [Google Antigravity](https://agentgid.com/agents/google-antigravity/): Google's agent-first development platform, introduced as an IDE based on a VS Code fork alongside Gemini 3. Antigravity 2.0 (2026-05-19) added a standalone desktop app for orchestrating parallel agents, next to the IDE, a CLI and an SDK. - [Kiro](https://agentgid.com/agents/kiro/): AWS's agentic IDE built around spec-driven development, with a CLI, Kiro Web for cloud sessions, a mobile app and the open-source Kiro Crew workspace. AWS positions it as the replacement for Amazon Q Developer's IDE plugins. - [ARTEMIS](https://agentgid.com/agents/google-artemis/): An agent that takes natural-language instructions and carries out multi-step tasks and test workflows on Android devices or emulators through ADB using multimodal models, with an MCP server so coding assistants can drive devices. - [Jasper](https://agentgid.com/agents/jasper/): An AI marketing platform that runs specialised agents for campaigns, SEO, personalisation, research and translation in a shared workspace, following brand voice and product knowledge stored in Jasper IQ. - [LlamaIndex](https://agentgid.com/agents/llamaindex/): A framework for building LLM applications and agents over your own data, covering document processing, retrieval and agent workflows. - [Agent Development Kit (ADK)](https://agentgid.com/agents/google-adk/): Google's open-source, code-first toolkit for building, evaluating and deploying AI agents, with SDKs for Python and TypeScript among other languages. - [Mem0](https://agentgid.com/agents/mem0/): A memory layer for AI agents and apps: it extracts facts from conversations, stores them and retrieves the relevant ones later, so an agent remembers users and past work across sessions. - [Eightfold AI Interviewer](https://agentgid.com/agents/eightfold-ai/): Runs first-round structured interviews in many languages, assessing skills from what candidates say, and summarises results for recruiters; it sits alongside Eightfold's candidate agent. - [Kilo Code](https://agentgid.com/agents/kilo-code/): Open-source coding agent available as a VS Code extension, JetBrains plugin and CLI, with a gateway to 500+ models and support for bring-your-own keys and local models. Kilo launched in March 2025 and was acquired by Anaconda in July 2026. - [Repomix](https://agentgid.com/agents/repomix/): Packs a whole repository, or the parts you choose, into one AI-friendly file with a token count per file, so you can give a codebase to a model or agent in one go. - [Genspark](https://agentgid.com/agents/genspark/): AI workspace built around a Super Agent that plans and runs multi-step tasks in a sandbox with a real browser and filesystem, producing slides, sheets, documents, research and websites. It also offers a Chrome extension, an AI browser, a Claw personal agent that can run in the cloud or locally, and in-house models such as Gen-1. - [Pydantic AI](https://agentgid.com/agents/pydantic-ai/): A Python agent framework from the Pydantic team, built around type-safe structured outputs, dependency injection and model-agnostic tool calling. - [Paradox](https://agentgid.com/agents/paradox/): Paradox's assistant Olivia automates candidate screening, interview scheduling, applications and onboarding over chat and SMS, mainly for high-volume hiring. Workday completed its acquisition of Paradox in October 2025. - [CodeGPT](https://agentgid.com/agents/codegpt/): AI coding agent and chat for VS Code and JetBrains IDEs with an agentic planning mode, multi-file edits, MCP support and custom agents. Works with Claude, GPT, Gemini, Grok and other models, your own API keys, or local models via Ollama and LM Studio. - [GitHub Copilot CLI](https://agentgid.com/agents/github-copilot-cli/): GitHub's standalone terminal coding agent (`copilot`, npm @github/copilot) that plans and edits code, runs commands and works with GitHub from the terminal. It runs on a Copilot plan and also supports bring-your-own model providers. - [Harvey](https://agentgid.com/agents/harvey/): An AI platform for law firms and in-house legal teams covering research, drafting, due diligence and document review, with pre-built and custom agents for multi-step legal work. - [Goose](https://agentgid.com/agents/goose/): Open-source, general-purpose AI agent that runs locally as a desktop app or CLI and can write code, run commands and use MCP extensions with 15+ LLM providers. Created by Block, it is now hosted by the Agentic AI Foundation at the Linux Foundation. - [Haystack](https://agentgid.com/agents/haystack/): deepset's open-source framework for building production LLM pipelines and agents, with a focus on retrieval. - [Phoenix](https://agentgid.com/agents/arize-phoenix/): Traces, evaluates and troubleshoots LLM apps and agents, built on OpenTelemetry, with prompt experiments and datasets. Runs locally, self-hosted or in the cloud. - [Tabnine](https://agentgid.com/agents/tabnine/): AI code assistant and agent delivered as IDE plugins (VS Code, JetBrains, Visual Studio), a CLI and an OpenCode plugin, with a context engine and private or self-hosted deployment for enterprises. - [Botpress](https://agentgid.com/agents/botpress/): Platform for building and deploying LLM-based support agents with a hosted studio, a conversation-metered pricing model and a public MIT-licensed monorepo of SDKs and integrations. It integrates with help desks such as Intercom, Zendesk, HubSpot and Salesforce. - [Decagon](https://agentgid.com/agents/decagon/): Platform for deploying AI agents that resolve customer support conversations over chat, email and voice, with workflows written as natural-language Agent Operating Procedures. It also provides testing, QA and analytics tooling for those agents. - [Copy.ai](https://agentgid.com/agents/copy-ai/): A go-to-market AI platform for building workflows and agents that automate marketing and sales tasks such as content generation, SEO articles, research and account planning. Fullcast acquired it in October 2025. - [Consensus](https://agentgid.com/agents/consensus/): An AI search engine for peer-reviewed research whose Deep Search mode plans many searches, reviews large numbers of papers and writes a cited, structured literature-review report. - [Qwen Code](https://agentgid.com/agents/qwen-code/): Alibaba's open-source terminal coding agent for Qwen models that also offers a desktop app, web UI, IDE plugins (VS Code, Zed, JetBrains) and SDKs. It accepts OpenAI-, Anthropic- and Gemini-style provider APIs as well as local models. - [Grok Build](https://agentgid.com/agents/grok-build/): xAI's terminal coding agent (`grok`): a full-screen TUI that edits files, runs shell commands and searches the web, with a headless/CI mode and Agent Client Protocol support for editors. Its Rust source is published under Apache-2.0 and synced from an internal monorepo. - [Lovart](https://agentgid.com/agents/lovart/): A web app that takes a brief or brand guidelines and generates design assets such as brand identities, ads, packaging, product shots and video on an infinite canvas, coordinating several image and video models. - [AnythingLLM](https://agentgid.com/agents/anything-llm/): An all-in-one AI application for chatting with documents, multi-user workspaces and built-in agents, including a no-code agent-flow builder and MCP compatibility; runs as a desktop app or self-hosted with Docker. - [Headroom](https://agentgid.com/agents/headroom/): Compresses tool outputs, logs, files, RAG chunks and conversation history before they reach the model, so agents use fewer tokens. Runs locally as a library, a proxy, an agent wrapper or an MCP server; originals stay cached and can be retrieved on demand. - [Langflow](https://agentgid.com/agents/langflow/): A visual, Python-based builder for AI agents and workflows that can also expose flows as APIs and MCP servers. - [BettaFish](https://agentgid.com/agents/bettafish/): An open-source multi-agent system that collects and analyses social-media posts and comments across platforms and writes public-opinion research reports; built in Python without an external agent framework. - [Forethought](https://agentgid.com/agents/forethought/): AI agent platform for support teams with a Solve agent that resolves tickets over chat, email, voice, API and Slack, plus Triage, Discover, QA and Assist products. Zendesk markets it as Forethought AI agents by Zendesk and it can run on other service platforms. - [Momentic](https://agentgid.com/agents/momentic/): An AI QA agent that explores a running app from a short description and reports findings, plus AI-written regression tests that update themselves when the UI changes and run locally or in CI. - [VoltAgent](https://agentgid.com/agents/voltagent/): An open-source TypeScript framework for building, orchestrating and observing AI agents. - [Emergent](https://agentgid.com/agents/emergent/): Conversational vibe-coding platform that builds full-stack web and mobile apps with AI agents, with private hosting, GitHub integration and agent building. It offers Free, Standard and Pro individual plans plus Business and Enterprise. - [nanobot](https://agentgid.com/agents/nanobot/): A lightweight, self-hosted personal agent runtime in Python that runs in a web UI, a terminal or chat apps, using shell, files, web, MCP and sub-agents, with long-term memory and scheduled automations. - [Chatbase](https://agentgid.com/agents/chatbase/): Platform for building AI support and sales agents trained on a company's own content and published to a website widget, WhatsApp, email, Slack and other channels. Plans are metered in monthly message credits, with model choice across several providers. - [Bolt.new](https://agentgid.com/agents/bolt-new/): Browser-based AI app builder from StackBlitz that generates, runs and deploys full-stack web apps and sites from prompts using in-browser WebContainers. It includes hosting, databases, team plans and Bolt Forge for open-source models. - [Legora](https://agentgid.com/agents/legora/): A legal AI platform for contract review, research and drafting whose agent plans and carries out multi-step legal tasks with review checkpoints for lawyers. - [Activepieces](https://agentgid.com/agents/activepieces/): An open-source automation platform with AI agent steps and MCP support, positioned as an alternative to closed workflow tools. - [Pipecat](https://agentgid.com/agents/pipecat/): An open-source Python framework for voice and multimodal conversational agents, maintained by Daily and the community. - [Base44](https://agentgid.com/agents/base44/): AI app builder that generates full-stack apps with a built-in backend, database, authentication and hosting from prompts, and also offers a CLI and SDK. It was founded by Maor Shlomo and acquired by Wix. - [Inworld AI](https://agentgid.com/agents/inworld-ai/): Inworld offers realtime speech-to-speech, TTS, STT and LLM routing APIs that game studios can use for NPCs that respond to player speech, world state and story context, with viseme timestamps for lip-sync. It works from Unreal, Unity or custom engines over REST, WebSocket or WebRTC, and games are now one of several markets alongside companions, education and voice agents. - [CustomGPT.ai](https://agentgid.com/agents/customgpt-ai/): Platform for building retrieval-based AI agents from a company's own documents and website content, available as a chat widget and through a RAG API with official SDKs. It targets support and research questions and offers custom enterprise builds. - [AutoGen](https://agentgid.com/agents/autogen/): Microsoft's open-source framework for multi-agent conversations and event-driven agent systems. - [AgenticSeek](https://agentgid.com/agents/agenticseek/): A self-hosted assistant designed to run on local models that can browse the web, write and run code and split tasks across specialised agents; it runs with Docker and supports optional cloud model APIs. - [AgentScope](https://agentgid.com/agents/agentscope/): A Python framework for building multi-agent applications with ReAct agents, tool and MCP management, model abstractions, pipelines and human-in-the-loop controls. - [CloakBrowser](https://agentgid.com/agents/cloakbrowser/): Stealth Chromium that passes every bot detection test. Drop-in Playwright replacement with source-level fingerprint patches. 30/30 tests passed. - [Semantic Kernel](https://agentgid.com/agents/semantic-kernel/): Microsoft's SDK for adding LLMs, plugins and agents to C#, Python and Java applications. - [Graphiti](https://agentgid.com/agents/graphiti/): Builds real-time knowledge graphs for AI agents from conversations and business data, tracking how facts change over time, so agents can query what is true now and what was true before. - [smolagents](https://agentgid.com/agents/smolagents/): A minimal Hugging Face library for agents that write and run Python code as their actions. - [Coze Studio](https://agentgid.com/agents/coze-studio/): ByteDance's open-source visual platform for developing AI agents, released from its Coze product. - [AutoGPT](https://agentgid.com/agents/autogpt/): Platform for building, deploying and running AI agents through a chat-based AutoPilot, a visual builder and a marketplace, offered as a paid hosted service or self-hosted. The original 2023 autonomous agent remains in the repository as AutoGPT Classic. - [Sourcegraph Cody](https://agentgid.com/agents/cody/): Sourcegraph's AI coding assistant for VS Code, JetBrains, Visual Studio, the web and a CLI, using code-search context. Free and Pro plans were discontinued in 2025 and it remains only as part of Sourcegraph Enterprise. - [MCP for Unity](https://agentgid.com/agents/mcp-for-unity/): MCP for Unity is an open-source bridge that lets AI assistants such as Claude Code, Cursor, VS Code, Windsurf, Cline and Gemini CLI manage assets, control scenes, edit scripts and automate tasks in the Unity Editor. It is a Unity package (git URL or OpenUPM) plus a Python MCP server, and its README says it is sponsored and maintained by Aura. - [Kimi Code](https://agentgid.com/agents/kimi-code/): Moonshot AI's coding agent, offered as the Kimi Code CLI (`kimi`), a desktop app and a VS Code extension; it is included in Kimi memberships and can also use a Moonshot API key or other providers. The CLI was rebuilt in Node.js in 2026 and replaces the archived Python Kimi CLI. - [Elicit](https://agentgid.com/agents/elicit/): An AI research platform that searches academic papers and runs a research agent, automated research reports and systematic literature review workflows (screening and data extraction). It spun out of the nonprofit Ought. - [SciSpace Agent](https://agentgid.com/agents/scispace/): SciSpace (formerly Typeset) is an AI research workspace whose agent runs multi-step literature reviews, systematic-review screening, data extraction from papers and database searches. - [mabl](https://agentgid.com/agents/mabl/): Creates, runs and repairs tests for web, mobile, API, accessibility and performance, and describes itself as an agentic testing platform. - [Lyro](https://agentgid.com/agents/tidio-lyro/): AI customer service agent from Tidio that now has its own site and pay-as-you-go credit pricing, and can be placed on Tidio chat or invited into other help desks such as Zendesk, Freshdesk, Salesforce and HubSpot. It lets customers choose among Claude, GPT and Gemini models. - [Trae](https://agentgid.com/agents/trae/): ByteDance's AI IDE (branded TraeCode) with an agent mode, offered alongside TraeWork, an AI work assistant with cloud tasks and a web version. - [Fin](https://agentgid.com/agents/intercom-fin/): AI customer agent that answers and resolves support conversations over chat, email, voice and messaging channels, either natively inside the Intercom helpdesk or on top of other help desks such as Salesforce, HubSpot and Freshdesk. It runs on the vendor's own Apex model suite. - [Typebot](https://agentgid.com/agents/typebot/): Visual chatbot and chat-form builder that can be embedded on websites or run on WhatsApp and self-hosted. The code is source-available under the Functional Source License (FSL-1.1-ALv2) rather than an OSI-approved open-source license. - [MaxKB](https://agentgid.com/agents/maxkb/): An open-source platform for building enterprise agents that combines retrieval pipelines, an agentic workflow engine, MCP tool use and multi-model support, commonly used for customer service and internal knowledge bases. - [Kortix](https://agentgid.com/agents/kortix/): Source-available 'AI operating system' that runs agents on cloud computers, each session in an isolated sandbox on its own git branch, with agents, skills, memory and connectors kept in one repository and work delivered through reviewable change requests. It works in Slack and Microsoft Teams, with any model provider and your own API keys, and grew out of the Suna agent project. - [GenericAgent](https://agentgid.com/agents/genericagent/): A small Python agent that gives a model control of a local computer through the browser, terminal, files, keyboard and mouse, screen vision and Android ADB, and saves each completed task as a reusable skill. - [Microsoft Agent Framework](https://agentgid.com/agents/microsoft-agent-framework/): Microsoft's open-source SDK for building, orchestrating and deploying agents and multi-agent workflows in Python and .NET. It is the successor to both AutoGen and Semantic Kernel. - [Mistral Vibe](https://agentgid.com/agents/mistral-vibe/): Mistral's coding agent, used as the `vibe` CLI, a VS Code extension (with a JetBrains plugin and web version) and powered by Devstral models. Since May 2026 Mistral brands its whole assistant, formerly Le Chat, as Vibe. - [Netomi](https://agentgid.com/agents/netomi/): Enterprise customer experience AI platform whose agents handle conversations over chat, email and voice for large consumer brands. Accenture Ventures invested in 2026 and the two companies announced a strategic partnership. - [Antigravity CLI](https://agentgid.com/agents/antigravity-cli/): Google's terminal interface (`agy`) to the Antigravity agent platform, built in Go and announced at Google I/O on 2026-05-19 as the replacement for Gemini CLI. It supports background and multi-agent workflows. - [Crush](https://agentgid.com/agents/crush/): Charm's terminal-based AI coding agent (TUI) that connects to many LLMs through OpenAI- and Anthropic-compatible APIs and supports LSP and MCP. Its source is public under the FSL-1.1-MIT license, which is source-available rather than OSI open source. - [Aider](https://agentgid.com/agents/aider/): Open-source AI pair-programming tool for the terminal that edits files in a local git repository and commits the changes. It works with multiple LLM providers using the user's own API keys. - [Bito](https://agentgid.com/agents/bito/): Runs codebase-aware AI reviews on pull requests in GitHub, GitLab and Bitbucket and in the IDE, with an optional self-hosted Docker agent. - [Traycer](https://agentgid.com/agents/traycer/): Open-source desktop app for planning and orchestrating AI coding agents (Claude Code, Codex, Cursor, OpenCode and others) in parallel, each in its own git worktree. Turns ideas into specs and tickets, supports agent-to-agent communication, code review of diffs, shared context across models, and team collaboration. - [Gorgias AI Agent](https://agentgid.com/agents/gorgias-ai-agent/): AI agent inside the Gorgias ecommerce help desk that answers customer tickets and chats using Shopify store data and can take order actions on email, chat, SMS and social channels. It is added to a helpdesk plan and billed per automated interaction. - [Zowie](https://agentgid.com/agents/zowie/): Enterprise AI agent platform for customer service that separates language handling from a deterministic Decision Engine, so refunds, claims and identity checks run by policy. It deploys one agent across voice, chat, app, email and contact-center channels and has an open agent SDK. - [Greptile](https://agentgid.com/agents/greptile/): Builds a graph index of a codebase and uses several agents to review pull requests for bugs, security issues and rule violations with full-repository context. - [Qodo](https://agentgid.com/agents/qodo/): An AI code review platform that reviews pull requests across repositories using codebase context and team rules, with IDE extensions for local review. - [Hugo](https://agentgid.com/agents/crisp/): Hugo is the AI support agent from Crisp, sold on its own site and run on top of a Crisp workspace; it answers customers from linked knowledge and resolves tickets, with a choice of Claude, ChatGPT, Llama or custom models. It uses AI credits that come with paid Crisp plans. - [Codebuff](https://agentgid.com/agents/codebuff/): Terminal coding assistant from CodebuffAI (formerly Manicode) that orchestrates multiple specialized agents, with an SDK for custom agents. The same team's ad-supported free product Freebuff is built on it and now shares its GitHub repository. - [Sourcery](https://agentgid.com/agents/sourcery/): Reviews GitHub and GitLab pull requests with bug findings, summaries, diagrams, one-click fixes and security scanning, and offers in-IDE reviews. - [Augment Code](https://agentgid.com/agents/augment-code/): AI coding platform built around a codebase Context Engine, delivered as VS Code and JetBrains extensions, the Auggie CLI and Cosmos, a platform for always-on cloud agents and software-delivery workflows. - [Hex](https://agentgid.com/agents/hex/): A data notebook and analytics platform whose Notebook Agent writes and runs SQL and Python to investigate questions, while Threads answers natural-language data questions and a modelling agent builds semantic models. - [Godot MCP](https://agentgid.com/agents/godot-mcp/): Godot MCP is an open-source MCP server that lets AI assistants launch the Godot editor, run projects in debug mode, capture debug output and inspect project structure. It can also create scenes, add nodes, load sprites, export MeshLibrary resources and manage UIDs (Godot 4.4+). - [Inkeep](https://agentgid.com/agents/inkeep/): Platform for building AI agents and assistants for customer experience and documentation, with a visual builder, a TypeScript SDK and chat components, offered as a source-available framework under the Elastic License 2.0 plus a managed Enterprise edition. Enterprise adds Slack, Discord, Teams, Zendesk and Salesforce integrations. - [PandasAI](https://agentgid.com/agents/pandasai/): A Python library that turns natural-language questions into Python and SQL, runs it against dataframes, databases and data lakes, and returns answers and charts. - [kapa.ai](https://agentgid.com/agents/kapa-ai/): Retrieval and answer platform that ingests a product's documentation, GitHub, forums and other sources and serves answers through a website widget, Slack bot, Zendesk agent, MCP server, API and SDKs. It is aimed at developer-product companies that want an ask-AI assistant on their docs. - [Amp](https://agentgid.com/agents/amp/): Coding agent and development environment from Amp, spun out of Sourcegraph, used through a CLI, a web app and macOS/iOS apps; each thread can run in a cloud 'orb' that keeps working after the laptop is closed. Users can bring their own model keys or link a ChatGPT subscription. - [AgentKit by Inngest](https://agentgid.com/agents/inngest-agentkit/): A TypeScript library for multi-agent networks with deterministic routing, built on Inngest's durable execution engine. - [PentAGI](https://agentgid.com/agents/pentagi/): A self-hosted multi-agent system that carries out penetration testing tasks in a sandboxed environment, written in Go and React and working with several model providers. - [Graphite](https://agentgid.com/agents/graphite/): A pull-request review platform for stacked PRs whose AI reviewer posts codebase-aware feedback, explains changes, proposes fixes and helps resolve CI failures. Cursor agreed to acquire Graphite in December 2025; it continues as a separate product. - [CodeRabbit](https://agentgid.com/agents/coderabbit/): Posts automated reviews, summaries and suggested fixes on pull requests, and also runs reviews in the IDE and from a command-line tool. - [CodeWhale](https://agentgid.com/agents/codewhale/): A provider-neutral terminal coding agent written in Rust that reads projects, edits files, runs commands and tests to check its work, with approval-based permissions, undo and sub-agents. It grew out of the deepseek-tui project. - [Uizard](https://agentgid.com/agents/uizard/): A UI design tool whose Autodesigner generates multi-screen, editable app and web designs from text prompts and changes components, screens and themes through further prompts. Uizard joined Miro in 2024. - [CAMEL](https://agentgid.com/agents/camel/): An open-source multi-agent framework and research community focused on agent societies and large-scale simulation. - [AirOps](https://agentgid.com/agents/airops/): A content platform whose agents and workflows research, create, refresh, publish and monitor content for AI search visibility and SEO, using brand kits and knowledge bases. - [Voiceflow](https://agentgid.com/agents/voiceflow/): Platform for designing and deploying AI agents that run across web, app, WhatsApp, SMS and voice, aimed at agencies building for clients and at businesses running customer experience. It offers a model picker across major providers and a Shopify integration app. - [CowAgent](https://agentgid.com/agents/cowagent/): A self-hosted assistant, formerly chatgpt-on-wechat, that plans tasks and runs tools, skills and browser automation with memory, a knowledge base and multi-agent teams, connecting to web, WeChat, Feishu, DingTalk, Telegram, Slack and other channels. - [PR-Agent](https://agentgid.com/agents/pr-agent/): A self-hostable agent that reviews, describes and suggests improvements on pull requests for GitHub, GitLab, Bitbucket, Azure DevOps and Gitea with a configurable model. Qodo handed it to an independent community organisation in 2026. - [WRITER Agent](https://agentgid.com/agents/writer/): An enterprise AI platform whose agent automates multi-step work across connected business apps using playbooks, scheduled routines, code execution, browser automation and web search; its published use cases centre on marketing and content. - [Letta](https://agentgid.com/agents/letta/): A platform for stateful agents with long-term memory that persists across sessions. Formerly known as MemGPT. - [Skyvern](https://agentgid.com/agents/skyvern/): Open-source platform that automates browser-based workflows with LLMs and computer vision, available as a self-hosted AGPL project with Python and TypeScript SDKs and as the managed Skyvern Cloud, which adds proxies and anti-bot measures. - [v0](https://agentgid.com/agents/v0/): Vercel's AI builder that turns prompts into full-stack web apps and UIs, with GitHub sync (branches and pull requests), Vercel deployment, a visual Design Mode, a model picker and an iOS app. - [Clay](https://agentgid.com/agents/clay/): Go-to-market data platform for building and enriching prospect lists from many data providers, with Claygent and account agents that research companies and people on the web. - [DocsBot AI](https://agentgid.com/agents/docsbot-ai/): Service for building AI support and documentation assistants trained on a company's docs, help center and ticket data, deployable as a website widget or on Slack, Messenger, WhatsApp and Telegram. Usage is metered in monthly AI credits that depend on the model used. - [GPT Researcher](https://agentgid.com/agents/gpt-researcher/): An open-source agent that plans research, gathers and filters many web or local sources and writes a cited report, with support for multiple model providers. - [MetaGPT](https://agentgid.com/agents/metagpt/): A multi-agent framework that assigns software-company roles such as product manager, architect and engineer to agents that collaborate on a task. - [DeerFlow](https://agentgid.com/agents/deerflow/): Open-source 'super agent' harness from ByteDance that orchestrates subagents, memory, skills and sandboxes for long-horizon research, coding and content-creation tasks. Version 2.0 is a ground-up rewrite of the original Deep Research framework. - [Command Code](https://agentgid.com/agents/command-code/): Coding agent for the terminal (command `cmd`) that learns a developer's coding "taste" from accepts, rejects and edits and stores it in a readable taste file. Built for open models (Kimi, DeepSeek, GLM, Qwen, MiniMax) as well as Claude and GPT; also ships a desktop app, headless mode, MCP, skills and hooks. - [QwenPaw](https://agentgid.com/agents/qwenpaw/): A self-hosted personal assistant built on AgentScope that runs locally, in Docker or in the cloud, with skills, plugins, MCP, multi-agent support, layered memory and scheduled tasks, and connects to chat channels such as DingTalk, Lark, Discord and Telegram. - [Stitch](https://agentgid.com/agents/google-stitch/): A Google Labs tool that generates and iterates mobile and web UI designs and front-end code from text, images or voice, with a design agent working on a shared canvas. It exports to Figma, AI Studio and Antigravity and has an MCP server and SDK. - [Open Interpreter](https://agentgid.com/agents/open-interpreter/): Open Interpreter is now a Rust-based terminal coding agent, a fork of OpenAI's Codex CLI, tuned to get strong results from low-cost open models such as Kimi K3, DeepSeek, Qwen and GLM. The original Python 'let language models run code' project continues as a community-maintained fork. - [AG2](https://agentgid.com/agents/ag2/): A community-driven continuation of the original AutoGen codebase, maintained as an open-source multi-agent framework. - [Kosmos](https://agentgid.com/agents/kosmos/): An AI scientist agent from Edison Scientific, a commercial spinout of FutureHouse. A run reads large amounts of literature, executes analysis code and produces cited reports. - [Lemonade](https://agentgid.com/agents/lemonade/): AI agent for making Roblox games from text prompts; users sign in with Roblox and describe a game (e.g. dodge, farm or shooter games) for the agent to build. - [Nanobrowser](https://agentgid.com/agents/nanobrowser/): A Chrome and Edge extension that runs a planner and navigator multi-agent system in the browser to carry out web tasks, using your own model API keys or Ollama. - [Amazon Nova Act](https://agentgid.com/agents/amazon-nova-act/): AWS service and Apache-2.0 Python SDK for building and running fleets of UI-automation agents that complete browser workflows from natural-language act() calls plus Python code and hand off to a human when needed. Workflows are developed in a web playground, IDE extension or CLI and deployed on AWS. - [Kiro CLI](https://agentgid.com/agents/kiro-cli/): AWS's terminal agent from the Kiro family (`kiro-cli`) for building applications with natural-language chat and automated workflows; sign-in uses Kiro accounts (social login or AWS Builder ID) and plans are credit-based. - [Strix](https://agentgid.com/agents/strix/): An open-source multi-agent penetration testing tool that runs dynamic tests against applications, validates findings with working proofs of concept and proposes fixes; it runs locally with Docker or as a hosted service. - [Rtk](https://agentgid.com/agents/rtk/): CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies - [Lindy](https://agentgid.com/agents/lindy/): AI teammate that lives in Slack and iMessage, connects to a team's tools through thousands of integrations and MCP, and handles inboxes, meetings and scheduled routines from a shared pool of credits; computer use is available on higher tiers. Earlier versions were centred on a no-code agent builder. - [Perplexity Comet](https://agentgid.com/agents/perplexity-comet/): Chromium-based AI browser from Perplexity with a built-in assistant that summarizes pages, answers questions across tabs and can act for the user, for example drafting email or shopping. It runs on Mac, Windows, Android and iOS. - [Julius AI](https://agentgid.com/agents/julius-ai/): An AI workspace that analyses uploaded files and connected data sources in conversation and produces charts, reports, dashboards and presentations. - [Sim](https://agentgid.com/agents/sim/): An open-source workspace for building, deploying and monitoring AI agent workflows on a visual canvas. - [Vellum](https://agentgid.com/agents/vellum/): Open-source personal AI assistant with long-term memory, proactive check-ins and sandboxed tool use that takes actions across your apps. Runs on Vellum Cloud or self-hosted, reachable from macOS/Windows apps, web, iOS, voice, email, Telegram and Slack, and extensible with plugins and custom skills. - [Scenario](https://agentgid.com/agents/scenario/): Scenario is a generative AI platform for game assets that offers hundreds of image, video, 3D (with PBR textures) and audio models, and lets teams train custom models on their own art style. Its agents turn a plain-language brief into a runnable workflow, and its API and MCP server connect it to Unity, Unreal, custom pipelines and coding agents such as Claude Code, Codex and Cursor. - [jcode](https://agentgid.com/agents/jcode/): A terminal coding agent written in Rust, designed to use little memory so many sessions can run in parallel, with support for several model providers, session memory, browser automation and multi-agent coordination. - [Claude Design](https://agentgid.com/agents/claude-design/): A Claude feature that builds visual designs, interactive prototypes, slides and one-pagers from a description, applies an imported design system and refines the result through chat or inline edits. Output exports to PDF, PPTX, HTML or partner tools such as Canva. - [Reasonix](https://agentgid.com/agents/reasonix/): A terminal coding agent written in Go that uses DeepSeek by default and any OpenAI-compatible endpoint, designed for long autonomous sessions, with plan mode, permissions, a workspace sandbox, checkpoints and MCP support. It is a community project, not affiliated with DeepSeek. - [Agent Zero](https://agentgid.com/agents/agent-zero/): Open-source agentic framework that runs in Docker with its own Linux environment, using and creating tools, a browser with DOM annotation, a desktop canvas, document editing, MCP and a plugin hub. Controlled through a web UI with your chosen LLM provider; a CLI connector bridges it to the host machine. - [Eigent](https://agentgid.com/agents/eigent/): A desktop app built on the CAMEL-AI multi-agent framework that runs single agents or a multi-agent workforce to automate tasks with browser, terminal, MCP and skill tools, fully locally or with Eigent's cloud backend. - [NanoClaw](https://agentgid.com/agents/nanoclaw/): A small TypeScript assistant that runs each agent in its own Linux container and connects to messaging apps such as Slack, Telegram, WhatsApp and Discord, with per-agent memory and scheduled tasks; built on the Claude Agent SDK with optional other providers. - [Claude Cowork](https://agentgid.com/agents/claude-cowork/): Anthropic's agent capability in the Claude apps for multi-step knowledge work: it breaks a goal into subtasks, uses local files, connectors and plugins, and returns finished files such as spreadsheets, slide decks and documents. Sessions can run in the cloud (beta) or on the desktop, and since September 2026 Cowork is built into every Claude conversation. - [Leon](https://agentgid.com/agents/leon/): A self-hosted personal assistant whose 2.0 developer preview adds an agent mode with step-by-step planning, tool use, layered memory and desktop and browser computer use, alongside deterministic skills. - [Checksum](https://agentgid.com/agents/checksum/): Generates Playwright end-to-end and API tests, runs them in CI and repairs failing tests automatically as the code changes. - [Maven AGI](https://agentgid.com/agents/maven-agi/): Enterprise AI agent platform for customer experience with AI agents, an agent designer and a voice agent, plus a unified inbox and data and insights tooling. It lists apps for Zendesk, Salesforce, Freshdesk and Slack and offers Node and Python SDKs. - [Artisan](https://agentgid.com/agents/artisan/): Sales platform built around Ava, an AI business development agent that sources leads from a B2B contact database, runs email and social outreach, handles replies and books meetings. - [Relevance AI](https://agentgid.com/agents/relevance-ai/): Platform for building and running teams of AI agents (an 'AI workforce') with tools, triggers, evaluations and enterprise controls, aimed at sales, support, marketing and operations work. It lists 2,000+ integrations, calling and meeting agents, and an API and MCP. - [Sierra](https://agentgid.com/agents/sierra/): Platform for building and running branded AI agents for enterprise customer service over chat, SMS, WhatsApp, email and voice. It includes Ghostwriter (an agent that builds and optimizes other agents), Agent Studio and Insights, and it is sold with outcome-based pricing. - [BeeAI Framework](https://agentgid.com/agents/beeai-framework/): An open-source framework for building production agents in Python and TypeScript, started at IBM Research. - [Testsigma Atto](https://agentgid.com/agents/testsigma-atto/): Runs a set of AI agents that plan, write, run, analyse and repair tests for web, mobile, desktop, API and Salesforce apps and score release readiness. - [Flowith](https://agentgid.com/agents/flowith/): Canvas-style AI workspace whose Flowith Neo agent runs long multi-step tasks such as research, slides, websites, images and video, keeping outputs as editable nodes on a canvas. It also sells access to third-party image and video models inside the canvas. - [Spring AI Alibaba](https://agentgid.com/agents/spring-ai-alibaba/): A Java and Spring framework for agentic, workflow and multi-agent applications, built on Spring AI with graph-based orchestration, context engineering, A2A and MCP support. - [Jules](https://agentgid.com/agents/jules/): Asynchronous coding agent from Google that clones a repository into a cloud VM, plans the work and opens pull requests using Gemini models. Tasks can be started from the web app, a GitHub issue label, the Jules Tools CLI or a REST API. - [Ada](https://agentgid.com/agents/ada/): AI agent platform for enterprise customer service that handles conversations over messaging, voice and email and orchestrates several LLMs. It ships web and mobile messaging SDKs, an API and an MCP server for integration. - [ZCode](https://agentgid.com/agents/zcode/): Desktop coding agent environment from Z.ai built around GLM-5.3, covering planning, coding, debugging, testing and change review from natural-language goals with multi-agent collaboration. Tasks can be started and steered remotely from WeChat, Feishu or Telegram; available for macOS, Windows and Linux. - [Cursor CLI](https://agentgid.com/agents/cursor-cli/): Cursor's terminal agent (`agent`), which runs Cursor's coding agent interactively or headlessly in the terminal, CI and scripts, with Agent, Plan and Ask modes and handoff to cloud agents. It uses a Cursor account and Cursor plans. - [NodeZero](https://agentgid.com/agents/horizon3-nodezero/): Horizon3.ai's autonomous pentesting platform that runs real attack techniques against internal, external, cloud, Kubernetes, Active Directory and web-app environments to show which weaknesses can be exploited. - [Parloa](https://agentgid.com/agents/parloa/): Enterprise platform for building, running and managing AI agents for contact centers, covering voice and chat with agent lifecycle management and model orchestration. It is sold on consumption pricing per voice minute and per chat interaction with custom volume packages. - [Firebase Studio](https://agentgid.com/agents/firebase-studio/): Google's browser-based, VS Code-derived workspace (formerly Project IDX) with Gemini agents and an App Prototyping agent for building full-stack apps. It is in wind-down: new workspaces are disabled and the service shuts down on 2027-03-22. - [PolyAI](https://agentgid.com/agents/polyai/): Enterprise voice AI platform for building dialog agents that handle customer calls, with Agent Studio, the Wren agent that improves other agents, and an Apache-2.0 ADK for local development. Voice use is priced per minute. - [ChatGPT Work](https://agentgid.com/agents/chatgpt-work/): ChatGPT's agent mode for longer multi-step tasks that end in finished deliverables such as documents, spreadsheets, presentations and sites. It runs in the cloud on web and mobile, and the ChatGPT desktop app can also use local files and apps with the user's permission. - [Juicebox](https://agentgid.com/agents/juicebox/): A recruiting platform built around PeopleGPT, a natural-language search over candidate profiles from many sources; its agents source and rank candidates continuously and can shortlist or email them. - [K8sGPT](https://agentgid.com/agents/k8sgpt/): Scans Kubernetes clusters with built-in analysers, diagnoses problems and explains them in plain English using a choice of model backends; runs as a CLI, server, MCP server or in-cluster operator. - [Typeface](https://agentgid.com/agents/typeface/): An enterprise marketing AI platform whose Arc Agents plan, create and check on-brand email, web, ad, image and video content, drawing on brand and audience knowledge; custom agents can be built in Agent Studio. - [Dia](https://agentgid.com/agents/dia/): Chromium-based AI browser for Mac from The Browser Company, now owned by Atlassian, that lets users chat with their tabs and connected work tools, with writing help, a daily Morning Brief and reports. Windows is announced as coming this fall, and the company stopped developing its earlier Arc browser to focus on Dia. - [Rosebud AI](https://agentgid.com/agents/rosebud-ai/): Rosebud AI is a browser-based platform where you describe a game in a prompt or pick a template, and the AI builds it so you can play, remix and share it without writing code. It also generates game assets such as 2D images, sprite animations, 3D models, sounds and skyboxes, and is aimed at people who want to make games without programming. - [Synthflow](https://agentgid.com/agents/synthflow/): Platform for building and deploying AI voice agents that handle inbound and outbound phone calls, with telephony, SIP and CRM or contact-centre integrations. - [SiteGPT](https://agentgid.com/agents/sitegpt/): Service that trains a customer-support chatbot on a website's content and deploys it as a widget, with handoff to tools such as Crisp, Slack and Zendesk. It also provides a TypeScript SDK, a CLI and an MCP server. - [Kustomer AI](https://agentgid.com/agents/kustomer/): AI layer of the Kustomer customer service CRM, with Concierge (customer-facing agent), Envoy (agent assist) and Architect (goal-driven optimization). Since March 2026 it is also sold as a standalone layer over other help desks, starting with Zendesk. - [Hebbia](https://agentgid.com/agents/hebbia/): An AI platform that analyses large sets of documents for asset managers, investment banks and law firms; its Matrix product uses an orchestrator agent that delegates retrieval, table building and synthesis to subagents. - [Coplay](https://agentgid.com/agents/coplay/): Coplay is an AI agent that runs inside the Unity Editor, installs through the Unity Package Manager, and handles engine tasks with as much autonomy as you allow. Coplay is now part of Aura and also offers Coplay MCP for use with your own AI subscription. - [Luminance](https://agentgid.com/agents/luminance/): An AI platform for contract negotiation, review and repository analysis whose agent takes natural-language instructions and carries out contract tasks such as mark-ups, approvals and reports. - [DeepCode](https://agentgid.com/agents/deepcode/): An open-source coding agent from HKUDS that coordinates specialised agents to turn natural-language requests and research papers into working code, with planning and verification steps; usable from the terminal, a desktop app or a web interface. - [Devin Desktop](https://agentgid.com/agents/devin-desktop/): Agentic IDE from Cognition, built on the Windsurf editor, that adds an Agent Command Center for managing local and cloud coding agents and supports third-party agents through the Agent Client Protocol. A JetBrains plugin continues under the Windsurf name. - [NiCE Cognigy](https://agentgid.com/agents/cognigy/): Cognigy.AI platform for building voice and chat AI agents for enterprise contact centers, with an agent copilot, now sold by NiCE alongside CXone. It lists integrations with NiCE, Genesys, Avaya, AWS, Microsoft and 8x8. - [HolmesGPT](https://agentgid.com/agents/holmesgpt/): An open-source agent that investigates production incidents and alerts across Kubernetes, Prometheus, Datadog and other sources to find root causes; a CNCF Sandbox project that runs as a CLI or in-cluster operator. - [Droid](https://agentgid.com/agents/droid/): Factory's software-engineering agent 'Droid', used through the Droid CLI (terminal UI with approvals, MCP, hooks, plugins and multi-agent Missions), a desktop app, an IDE extension, an SDK and headless `droid exec` for CI. - [STORM](https://agentgid.com/agents/storm/): An open-source system from Stanford that researches a topic through web search and multi-perspective question asking, then writes a full-length, Wikipedia-style report with citations. - [Regie.ai](https://agentgid.com/agents/regie-ai/): Sales prospecting workspace whose AI agents source and enrich contacts, draft emails, dial through a power dialer and orchestrate multichannel outreach. - [testRigor](https://agentgid.com/agents/testrigor/): Turns plain-English test steps or high-level goals into executed end-to-end tests across web, mobile, desktop, API, email, SMS and 2FA flows, with self-healing maintenance. - [Spellbook](https://agentgid.com/agents/spellbook/): An AI tool for contract drafting, review and comparison that runs as a Microsoft Word add-in; its Associate agent works through multi-document legal tasks under a lawyer's supervision. - [MiMo Code](https://agentgid.com/agents/mimo-code/): A terminal coding agent from Xiaomi's MiMo team that reads and writes code, runs commands, manages Git and keeps memory across sessions. It is built on OpenCode with added context management and multi-agent orchestration. - [Convai](https://agentgid.com/agents/convai/): Convai is a platform for building conversational AI characters and NPCs with backstories, 500+ voices, 60+ languages, a knowledge bank, narrative design and environment-aware actions. Game, XR and simulation developers deploy them through a web playground and Unity and Unreal Engine plugins. - [Bland AI](https://agentgid.com/agents/bland-ai/): Platform for building, monitoring and improving AI phone agents for inbound and outbound calls, with speech recognition, language model and speech synthesis bundled into a per-minute rate. - [AiSDR](https://agentgid.com/agents/aisdr/): AI sales agent that finds prospects from buying signals and sends personalised outreach by email, LinkedIn and phone to book meetings, with HubSpot and Salesforce integration. - [KaneAI](https://agentgid.com/agents/kaneai/): Writes, runs and updates web and mobile tests from natural-language instructions and requirement documents, with self-healing and result analysis. The open-source Kane CLI exposes it to developers and coding agents. - [openJiuwen](https://agentgid.com/agents/openjiuwen/): Open-source platform for building production-grade AI agents, made up of Agent Core (Python SDK and runtime for agents, workflows, tool calls and prompt optimization), Agent Studio (low-code visual builder), Agent Runtime, DeepSearch, the JiuwenSwarm multi-agent workspace and a skills hub. - [11x](https://agentgid.com/agents/11x/): Provides AI "digital workers", chiefly Alice, an outbound sales development agent that researches accounts and runs multichannel outreach, and Julian, an inbound phone and lead-qualification agent. - [XBOW](https://agentgid.com/agents/xbow/): An autonomous offensive security platform that attacks web applications, chains findings into working exploits and reports vulnerabilities with reproducible proof, for continuous testing rather than periodic manual pentests. - [Aura](https://agentgid.com/agents/aura/): Aura is an AI agent for Unreal Engine and Unity developers that builds features, playtests them and finds bugs; self-playtesting is Unreal-only for now. In Unreal it installs as an engine-level plugin (UE 5.4–5.8 on Windows), and in Unity it uses the AuraForUnity desktop app, which bridges into the Editor. - [CAI (Cybersecurity AI)](https://agentgid.com/agents/cai/): A Python framework from Alias Robotics for building and running AI security agents for reconnaissance, exploitation, privilege escalation and defensive tasks, with guardrails and human-in-the-loop controls. - [Ziva](https://agentgid.com/agents/ziva/): Ziva is an AI agent plugin for Godot 4 that reads your scene tree and scripts, edits nodes from chat, writes GDScript or C#, inspects editor errors and helps test the game. It supports Godot 4.2+ on Windows, macOS and Linux, and its Pro and Ultra plans include a Playtest Agent. - [Agentforce for Service](https://agentgid.com/agents/salesforce-agentforce/): Salesforce's agent platform with prebuilt service agents that answer and act on customer requests over web, voice, SMS and WhatsApp using Service Cloud and CRM data. Salesforce completed its acquisition of the separate Fin agent (formerly Intercom) in September 2026. - [FinRobot](https://agentgid.com/agents/finrobot/): An open-source platform that combines model agents with quantitative tools for financial analysis, including a multi-agent equity research system in which valuation numbers are computed in code. - [Ludo.ai](https://agentgid.com/agents/ludo-ai/): Ludo.ai generates game assets such as sprites, animations, icons, UI, textures, music, sound, 3D models and video, and can preview gameplay mechanics as generated video before you build them. Developers using Unity, Unreal or Godot can reach it through a web app, a Unity plugin, a REST API, a hosted MCP server and a CLI aimed at coding agents such as Claude Code. - [Opera Neon](https://agentgid.com/agents/opera-neon/): Agentic AI browser from Opera for macOS and Windows with built-in agents (including a Deep Research agent) and access to many third-party models, which external agents can also drive over MCP or a CLI. The browser downloads for free, but its built-in agentic features need a subscription. - [Undermind](https://agentgid.com/agents/undermind/): An AI literature-search agent that asks clarifying questions, then searches and evaluates hundreds of papers and follows citation trails to find the most relevant work. - [Powerdrill Bloom](https://agentgid.com/agents/powerdrill/): An AI data analysis workspace that answers natural-language questions across documents, spreadsheets and databases with charts and tables, cites the source rows and runs scheduled analysis agents. - [Layer](https://agentgid.com/agents/layer-ai/): Layer is a generative AI platform for game studios that combines image, video, 3D and audio generation from 300+ models, custom style training and node-based workflows in one workspace. Its optional Layer Agent can research, ideate, pick models and build workflows, and it is also available to tools like Claude Code, Cursor and Codex through MCP, a CLI and Agent Skills. - [QA Wolf](https://agentgid.com/agents/qa-wolf/): Uses AI to map an application and generate Playwright and Appium tests, runs them in parallel on hosted infrastructure, and offers a managed service where QA engineers maintain the suite. - [Resolve AI](https://agentgid.com/agents/resolve-ai/): An AI SRE platform whose agents triage alerts, investigate incidents to find the root cause and automate operational tasks such as watching deploys and tuning alerts. - [Rillet](https://agentgid.com/agents/rillet/): An accounting ERP and general ledger for finance teams whose agents automate close and accounting workflows, flag anomalies, propose accruals and connect to other tools through MCP. - [Figma Make](https://agentgid.com/agents/figma-make/): A Figma feature that turns prompts, existing designs or design-system context into working prototypes and app code, which the user refines by further prompting or direct edits. - [EvenUp](https://agentgid.com/agents/evenup/): An AI platform for personal-injury law firms covering intake, treatment tracking, demand letters, negotiation, discovery and trial preparation, with communication agents and automated workflows. - [Alex](https://agentgid.com/agents/alex-ai-recruiter/): An AI recruiter that screens resumes, runs first-round interviews over video, phone, SMS or WhatsApp, checks candidate identity and fraud risk, and schedules follow-ups through applicant tracking integrations. - [Basis](https://agentgid.com/agents/basis/): Builds AI agents that carry out accounting work for accounting firms, including bookkeeping and advisory, tax return preparation and audit, with accountants reviewing the output. - [Bezi](https://agentgid.com/agents/bezi/): Bezi is a game development assistant that runs as a Unity engine plugin with full live project context, and it plans and then carries out work in the engine, such as building features, fixing bugs, creating UI, managing packages and running tests. It applies changes step by step through its own action system rather than MCP, and is aimed at Unity developers and teams. - [Claude in Chrome](https://agentgid.com/agents/claude-in-chrome/): Anthropic's Chrome extension that lets Claude read pages, click, type, navigate and fill forms in the user's own logged-in browser, including autonomous multi-step actions that a safety classifier checks before they run. It also connects to Claude Code and Cowork. - [Cleric](https://agentgid.com/agents/cleric/): An AI SRE that checks deployed changes against production traffic, triages and investigates alerts and hands off fix pull requests; read-only by default. - [Databricks Genie](https://agentgid.com/agents/databricks-genie/): A natural-language analytics agent in Databricks that answers questions over governed Unity Catalog data; its Agent Mode plans multi-step analyses and iterates over queries. - [Do Browser](https://agentgid.com/agents/do-browser/): AI agent delivered as a Chrome extension that controls the browser from natural-language instructions. Connects to ChatGPT, Claude or a Gemini API key, supports skills and a virtual filesystem that can mount local folders; runs on Chrome for Mac, Windows and Linux. - [Dropzone AI](https://agentgid.com/agents/dropzone-ai/): An AI SOC analyst that investigates security alerts end to end across connected SIEM, EDR, cloud, identity and email tools and returns a verdict with the evidence and reasoning. - [Fellou](https://agentgid.com/agents/fellou/): Agentic browser for Mac and Windows that plans and executes multi-step web workflows, research reports and desktop file tasks, with scheduled tasks, agentic memory and real-time intervention. The maker also publishes the open-source Eko agent framework. - [Gemini Spark](https://agentgid.com/agents/gemini-spark/): Google's 24/7 personal AI agent in the Gemini app: it runs tasks, schedules and reusable skills in the background across Gmail, Calendar, Drive, Docs and other Google apps, and can browse the web through Chrome auto browse or a remote browser. It requires a Google AI Pro or Ultra subscription and is not offered in the EEA, UK, Switzerland or Nigeria. - [Microsoft Copilot Studio](https://agentgid.com/agents/microsoft-copilot-studio/): Microsoft's low-code studio for building, governing and publishing AI agents, workflows and agent flows to Teams, Microsoft 365 Copilot, websites and other channels. It supports several model providers, MCP and agent-to-agent connections, and computer-use agents that became generally available in May 2026. - [Mintlify Assistant](https://agentgid.com/agents/mintlify-assistant/): AI assistant built into documentation sites hosted on Mintlify, a documentation platform for developer products; it answers questions from the docs and is metered in AI credits. The Mintlify CLI is distributed on npm. - [Perplexity Computer](https://agentgid.com/agents/perplexity-computer/): Perplexity's general-purpose agent that takes a goal in natural language and deploys subagents across several frontier models to research, build apps, websites and reports, and work in connected apps, including Slack and Microsoft 365. A Personal Computer mode works on local files on Mac and Windows. - [PostQode](https://agentgid.com/agents/postqode/): IDE extension for VS Code, Cursor and Windsurf with AI agents for planning, coding, testing and deployment. Includes Plan and Agent modes plus API, web (Playwright/Cypress/Selenium), unit and mobile (Appium) test agents, MCP integrations with tools like Jira and GitHub, and support for 40+ model providers. - [Rogo](https://agentgid.com/agents/rogo/): An AI platform for investment banks and investment firms that runs agents for multi-step work such as deal screening, diligence, Excel models, memos and slide decks. - [Traversal](https://agentgid.com/agents/traversal/): An enterprise AI SRE platform that investigates production incidents by testing many hypotheses in parallel over a model of the production system; deployed read-only, with bring-your-own-cloud options. - [Adobe GenStudio agents](https://agentgid.com/agents/adobe-genstudio-agents/): Agents in Adobe GenStudio and Workfront that turn campaign briefs into on-brand creative variants, draft briefs and automate planning and review workflows. - [Bits AI SRE](https://agentgid.com/agents/datadog-bits-ai-sre/): A Datadog agent that investigates alerts as they fire, forming hypotheses and querying Datadog telemetry to find root causes, with Slack, Jira, ServiceNow and GitHub integrations. - [Canva AI](https://agentgid.com/agents/canva-ai/): A conversational assistant in Canva that uses Canva's design engine to produce layered, editable designs, copy and images from a prompt and revise them over a conversation. Canva describes version 2.0 as agentic orchestration. - [Clio Work](https://agentgid.com/agents/clio-work/): Clio's AI workspace for legal research, matter analysis, drafting and document review, built on vLex's legal library; since April 2026 it can carry out goal-based multi-step tasks. - [CoCounsel Legal](https://agentgid.com/agents/cocounsel/): Thomson Reuters' AI for legal research, analysis and drafting built on Westlaw and Practical Law content; its deep research and guided workflows plan multi-step work and return cited reports. - [Compass](https://agentgid.com/agents/help-scout-ai-answers/): Help Scout's AI support agent that answers website and in-app chats from a team's own content within its guardrails and hands off to humans, billed per resolution on top of a Help Scout plan. Email handling is listed as coming soon. - [ConverzAI](https://agentgid.com/agents/converzai/): A virtual recruiter that runs candidate interviews and recruiting workflows for staffing agencies and writes the results back to applicant tracking systems such as Bullhorn and JobDiva. - [Freddy AI Agent](https://agentgid.com/agents/freshworks-freddy-ai-agent/): Freshworks' AI agent for its Freshdesk help desk and Freshchat messaging that answers customer requests from linked knowledge sources and can act through connectors. Paid Freshdesk plans include a quota of sessions and further sessions are sold in packs. - [Gemini Enterprise for Customer Experience (CX Agent Studio)](https://agentgid.com/agents/google-conversational-agents/): Google Cloud's builder and runtime for conversational customer service agents, powered by Gemini, covering chat, voice, email and social channels; its deterministic Flows edition is Dialogflow CX and its generative Playbooks edition builds agents from natural-language instructions. Pricing is metered per request or per second of audio. - [Gemini in Chrome (auto browse)](https://agentgid.com/agents/gemini-in-chrome/): Gemini assistant built into Chrome that summarizes pages, compares tabs and works across Google apps, with an auto browse preview that completes multi-step web tasks such as booking appointments while the user stays in control. Auto browse launched in preview in the US for Google AI Pro and Ultra subscribers. - [HubSpot Customer Agent](https://agentgid.com/agents/hubspot-breeze-customer-agent/): HubSpot's built-in AI support agent (also called Breeze Customer Agent) that answers customer questions and takes actions in the HubSpot CRM across chat, email, forms, voice, WhatsApp and Facebook Messenger. It requires HubSpot Professional or Enterprise editions and runs on HubSpot Credits. - [HubSpot marketing agents](https://agentgid.com/agents/hubspot-breeze-marketing-agents/): Agents in HubSpot that draft blog posts, LinkedIn articles, social posts and campaign assets from CRM data and brand voice, and suggest and schedule social posts for review. - [HubSpot Prospecting Agent](https://agentgid.com/agents/hubspot-prospecting-agent/): HubSpot Breeze agent that watches buying signals, sources contacts matching an ideal customer profile and drafts personalised outreach for sales reps inside HubSpot. - [incident.io AI SRE](https://agentgid.com/agents/incident-io-ai-sre/): incident.io's AI SRE starts investigating as soon as an incident is declared, correlating telemetry, code changes and past incidents, and reports cited hypotheses with confidence scores. - [Ito](https://agentgid.com/agents/ito/): AI QA agent that runs your app on every GitHub pull request. It reads the diff, builds the app in an isolated single-use sandbox, tests the affected user flows with computer-use agents without test scripts, and posts video, logs and repro steps to the PR. - [Microsoft Copilot (Edge Copilot Mode / Actions)](https://agentgid.com/agents/microsoft-copilot-consumer/): Microsoft's consumer Copilot assistant in Edge, which reasons across open tabs, groups browsing into Journeys and connects to Microsoft 365 apps; it began as the experimental Copilot Mode in Edge in July 2025, alongside Copilot Actions for tasks such as bookings (introduced April 2025). Microsoft started merging the consumer Copilot app with Microsoft 365 Copilot into one Copilot app in August 2026. - [Microsoft Security Copilot agents](https://agentgid.com/agents/microsoft-security-copilot-agents/): Microsoft-built and partner-built agents inside Defender, Entra, Intune, Purview and Sentinel that handle tasks such as phishing triage, data-loss alert triage, Conditional Access optimisation and vulnerability remediation. - [MiniMax Agent](https://agentgid.com/agents/minimax-agent/): MiniMax's general-purpose agent for research, coding, documents, slides and multimodal creation, offered on the web at agent.minimax.io and as a desktop app. The desktop app supports agent teams, scheduled tasks, MCP servers, a built-in browser with computer use, and MiniMax-managed or custom models. - [Mira](https://agentgid.com/agents/mira/): Personal AI assistant that runs inside Telegram as a bot (@mira) and Mini App, in private and group chats. It automates workflows on demand or on a schedule, sends briefings and reminders, summarizes group discussions, and connects to external apps such as GitHub, Notion and Google Drive. - [Proto](https://agentgid.com/agents/proto-agent/): Desktop AI agent for business teams from ERP.AI that works from plain-language requests across local files, ERP.AI records and apps, and the web in a built-in browser - checking records, preparing reports, or building no-code ERP, CRM and supply-chain systems. Asks for approval before actions like payments. - [Ramp agents](https://agentgid.com/agents/ramp-agents/): Agents built into Ramp's spend-management platform that apply expense policies, code invoices to ledger accounts, recommend approvals, flag possible fraud and handle accounts-payable steps. - [Roblox Assistant](https://agentgid.com/agents/roblox-assistant/): Assistant is built into Roblox Studio and pairs an LLM with a run-command system that can create, modify and delete objects and scripts, insert Creator Store assets, and generate materials, meshes and procedural models. It has a Planning Mode, where you review an editable plan before it runs, and a screen-capture subagent, and it is meant for Roblox creators. - [Roblox Studio MCP server](https://agentgid.com/agents/roblox-studio-mcp/): Roblox Studio has a built-in MCP server, turned on from Assistant's Manage MCP Servers menu, that lets an external AI client read the game's structure, edit scripts, run Luau, insert assets, playtest, capture the screen and simulate player input. It runs locally over stdio and has quick-connect setup for Claude Code, Claude Desktop, Codex CLI, Cursor, Gemini CLI, VS Code and Antigravity. - [Rovo Dev CLI](https://agentgid.com/agents/rovo-dev-cli/): Atlassian's terminal coding agent, run as an extension of the Atlassian CLI (`acli rovodev`), that works with Jira work items and repositories. Atlassian says Rovo Dev is reaching end of life as a standalone product, with capabilities moving into Jira subscriptions. - [Snowflake CoWork](https://agentgid.com/agents/snowflake-cowork/): A Snowflake agent built on Cortex Agents that answers questions over structured and unstructured enterprise data with charts and citations, runs research reports and multi-step skills, and can act in connected tools. It was renamed from Snowflake Intelligence in June 2026. - [Tezi](https://agentgid.com/agents/tezi/): Tezi's agent Max sources and screens candidates, answers their questions, schedules interviews and manages follow-ups, driven through Slack and email and working with an existing or built-in applicant tracking system. - [ThoughtSpot Spotter](https://agentgid.com/agents/thoughtspot-spotter/): An AI analyst agent in ThoughtSpot that answers business questions over enterprise data, reasoning through steps and checking its results; related agents build semantic models and dashboards. - [Unreal MCP](https://agentgid.com/agents/unreal-mcp/): Unreal MCP is an experimental Unreal Engine 5.8 plugin (ModelContextProtocol) that runs an MCP server inside the Unreal Editor, so AI agents can call engine functions such as spawning actors, setting up lighting, creating material instances and running automation tests. It listens only on local HTTP/SSE, can generate client configs for Claude Code, Cursor, VS Code, Gemini and Codex, and supports custom tools. - [Zapier Agents](https://agentgid.com/agents/zapier-agents/): Zapier's no-code builder for AI agents that act across 9,000+ connected apps, run on schedules or triggers, browse the web, call other agents and can be used from a Chrome extension. It is sold as an activity-based add-on to Zapier accounts. - [Zendesk AI agents](https://agentgid.com/agents/zendesk-ai-agents/): AI agents built into the Zendesk service suite that handle customer requests over messaging, email and voice and are billed per automated resolution. Zendesk also sells Forethought's AI agents, acquired in March 2026, which can run on other service platforms. ## Guides - [Best Claude Code Alternatives in 2026: Open-Source, Cheaper and Multi-Model](https://agentgid.com/guides/claude-code-alternatives/): The strongest alternatives to Claude Code, grouped by why you are switching: price, model choice, open source or a different workflow. Live usage and prices for each. - [How to Cut Token Usage in Claude Code and Cursor (2026)](https://agentgid.com/guides/reduce-claude-code-cursor-token-usage/): Practical ways to spend fewer tokens with Claude Code and Cursor: measure first, keep context small, match the model to the task, filter what the agent reads, and the open-source tools that help. - [AI Agent vs Chatbot vs Agentic AI: What Is the Difference?](https://agentgid.com/guides/ai-agent-vs-chatbot-vs-agentic-ai/): Plain-language definitions of AI agents, chatbots, agentic AI, LLMs, workflows and skills, how they relate, and how to tell which one you are looking at, with real examples. - [Best AI Agents in 2026: Live Rankings by Category](https://agentgid.com/guides/best-ai-agents/): The leading AI agents for coding, design, research, data, marketing, sales, support, HR, finance, legal, DevOps and security, ranked by public usage data that refreshes daily, with prices and free options. - [How to Build an AI Agent: No-Code Builders, Frameworks and SDKs](https://agentgid.com/guides/how-to-build-an-ai-agent/): A practical guide to building your first AI agent: choosing between no-code builders, open-source frameworks and model vendors' SDKs, the core agent loop, tools, guardrails and testing, with live usage data for each option. - [What Is an AI Agent? A Practical Explanation With Real Examples](https://agentgid.com/guides/what-is-an-ai-agent/): What makes software an AI agent, how agents differ from chatbots and plain language models, the main types in use today and how to judge one. - [AI Agent Statistics 2026: Live Usage, Growth and Activity Data](https://agentgid.com/guides/ai-agent-statistics/): Current statistics on AI agents from public data: package downloads, editor installs, GitHub stars, pull requests opened by coding agents, release pace and benchmark results. Updated daily. - [AI Customer Support Agents: Pricing Models and What They Cost](https://agentgid.com/guides/ai-customer-support-agent-pricing/): How AI agents for customer and technical support are priced: per resolution, per conversation, credits or seats, with the listed prices of the main products and what to check before you commit. - [Best AI Coding Agents in 2026: Ranked by Usage, Benchmarks and Price](https://agentgid.com/guides/best-ai-coding-agents/): The AI coding agents developers use most, with live download and install numbers, benchmark results, entry prices and a way to choose between terminal, IDE and cloud agents. - [Claude Code vs Codex vs Cursor: Usage, Price and Benchmarks Compared](https://agentgid.com/guides/claude-code-vs-codex-vs-cursor/): The three most discussed AI coding agents side by side on live data: downloads, installs, GitHub activity, release cadence, benchmark results and pricing. - [How to Start Using a Terminal Coding Agent: Setup, First Tasks and Guardrails](https://agentgid.com/guides/how-to-start-with-a-terminal-coding-agent/): A practical manual for your first week with a command-line coding agent: installing one, running a first session, writing project instructions, setting permissions and keeping costs under control.