- A0Cleaner — Automatic bulk cleanup of aged download caches, installer leftovers, retired browser profiles, inactive-chat screenshots, temporary captures, and unused Chromium versions.
- Scheduled task catch-up after downtime — Recurring tasks that were missed while the system was offline now run exactly once on the next tick, coalescing missed occurrences.
- Plugin maintenance tasks — Plugins can now own scheduled tasks that execute through the A0 task scheduler without creating an agent chat or calling a model.
- Time Travel snapshot expiry enabled by default — New installations and legacy configurations without the key now keep up to 500 recent snapshots within 30 days, plus current-state and boundary…
- Time Travel retention and capture controls — Workspace-relative exclusions, optional file-size limits, skipped-file reporting, and configurable history storage.
- Idle browser resource release — The shared Chromium, Xvfb, and Xpra runtime now suspends after one hour of inactivity, preserving saved tab URLs and the shared sign-in profile.
Agent Zero by Agent Zero s.r.o.
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.
Use it in: Web app CLI Desktop app Works with: MCP Local models Multi-agent Headless / CI
On this page
Usage data: latest readings Nov 21 to Nov 22, 2026, last checked Nov 22, 06:27 UTC. Date of each number
What Agent Zero does
Agent Zero is an open-source autonomous agent framework from Agent Zero s.r.o., first released in June 2024. You use it through a web app, a command-line tool and a desktop app. Its documentation covers MCP servers, subagents or parallel agents, a non-interactive mode for scripts and CI and local models. It is free and open source (MIT); you pay only for the models it calls.
Key facts
| Maker | Agent Zero s.r.o. |
|---|---|
| Type | Open-source autonomous agent framework |
| First released | June 2024 |
| License | MIT |
| Interfaces | Web app, CLI, Desktop app |
| Main language | Python |
| Open issues and PRs | 182 |
Pricing
Free, MIT-licensed open source; you supply your own LLM provider. No pricing page found on the official site.
Source: official pricing page, checked Oct 8, 2026. Prices change often; confirm before you buy.
Quick answers
- Free to start?Yes
- Open source?Yes (MIT)
- Where you use itWeb app, CLI, Desktop app
- Supports MCP?Yes
- Model providersopenrouter, local
- Subagents / multi-agent?Yes
- Runs in scripts / CI?Yes
- Feature comparisonAll agents
- Closest alternativeLangChain · all alternatives
What's new in Agent Zero: November 2026 so far
November brought significant architectural improvements to Agent Zero, including extraction of bundled tools into plugins, unified memory operations, and new cleanup and scheduling capabilities. The month focused on cleaner interfaces, better resource management, and streamlined tool architecture.
- Bundled tools are now available as standalone plugins with per-action permission controls.
- Memory operations consolidated into a single tool with action arguments for simpler integration.
- Automatic cleanup system removes aged caches, temporary files, and unused browser versions.
- Scheduled tasks now catch up after downtime and plugins can own their own maintenance tasks.
2 releases this month · summarised from the official release notes · all months
Get started with Agent Zero
Setup instructions are in the official documentation.
Add-ons for Agent Zero: save tokens, add memory and tools
LiteLLM
One gateway for 100+ models with spend tracking, budgets, rate limits and fallbacks.
Langfuse
Traces every model and tool call with its cost and latency, and runs evaluations.
Firecrawl
Turns websites into clean Markdown or structured data the agent can read.
E2B
Runs agent-written code in isolated cloud sandboxes instead of on your machine.
Composio
Connects the agent to 1,000+ apps and APIs with managed sign-in.
Mem0
Adds long-term memory, so the agent remembers users and past work across sessions.
Listed because each tool documents support for Agent Zero or for agent frameworks in general. Savings and results depend on your workload.
Agent Zero alternatives
Best Agent Zero alternatives compared · All agent frameworks and SDKs
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | Price | |||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 |
LangChainLangChain |
79 | 41.8M | up 6.2% | down 2.3% | 150K+70/day | 1.5.24d ago | Free (OSS) | |||
| 2 |
LangGraphLangChain |
75 | 20.5M | up 6.8% | up 27.4% | 45.2K+42/day | 1.2.242d ago | Free (OSS) | |||
| 3 |
AI SDKVercel |
67 | 48.6M | up 6.6% | up 31.2% | 28.1K+24/day | 7.0.1792d ago | Free (OSS) | |||
| 4 |
Claude Agent SDKAnthropic |
65 | 30.7M | up 10.0% | up 36.6% | 8,614+10/day | 0.2.1872d ago | Free (OSS) | |||
| 5 |
MastraMastra |
64 | 4.1M | up 24.5% | up 41.6% | 29.7K+31/day | 1.84.04d ago | Free (OSS) | |||
| 6 |
OpenAI Agents SDKOpenAI |
61 | 7.2M | up 4.1% | up 36.8% | 30.8K+19/day | 0.25.04d ago | Free (OSS) | |||
Ratings from people who use Agent Zero
No ratings yet. Used Agent Zero? Rate it and say what it is good and bad at.
Agent Zero news
-
Agent Zero 2.16 released
A0Cleaner — Automatic bulk cleanup of aged download caches, installer leftovers, retired browser profiles, inactive-chat screenshots, temporary captures, and unused Chromium versions.; Scheduled task catch-up after downtime — Recurring tasks that were missed…
What changed: recent Agent Zero releases
6 stable releases in the last 90 days · Monthly summary · Full changelog
- Extracted bundled tools into standalone plugins: wait, notify_user, search_engine, a2a_chat, scheduler, behavior_adjustment, and the scheduler Tasks UI are now standard plugins, each with…
- Unified memory tools: The four separate memory_load, memory_save, memory_delete, and memory_forget tools are consolidated into a single memory tool with an action argument, matching the…
- Per-action tool permissions: Profiles can now allow or deny individual operations across all 12 bundled multi-action tools…
- Centralized boolean argument coercion across all promoted and core tools, removing duplicated helpers and strict-validation error paths.
- Dedicated badge rendering for goal, document_query, skills, vision, browser, office, and computer_use_remote tool calls, each with distinct accent colors and descriptive headlines.
- Dropped agent-name prefix from all tool log headlines, warning rows, and fallback entries for cleaner chat output.
Earlier releases
- Significantly faster startup and chat loading — Embedding warm-up now overlaps with chat restoration and startup watchdogs, reducing median boot-to-first-token by ~27% and chat-switch latency by…
- Upgraded LiteLLM (1.104.0) and OpenAI SDK (2.54.0) with an automatic startup migration for existing Docker instances, including installed-SDK HTTP test coverage.
- Native LiteLLM routing for core providers — Nebius, Venice chat, Z.AI/Coding, and OpenRouter embeddings now use LiteLLM's built-in integrations, simplifying provider configuration while preserving…
- Responses prompt caching fix for long conversations — Completed Responses turns now retain masked extras at their original boundaries, preventing growing conversations from discarding cacheable…
- Reduced browser startup and rendering overhead — avoids launching Chromium for empty tab listings, eliminates redundant load waits, and reuses native viewer display size.
- Simplified Browser quick settings to focus on preset, Host/Container, zoom, and extensions; moved extension management and Chromium settings pages into Browser config.
- Redesigned file browser navigation — configurable path bar with breadcrumb and text modes, folder autocomplete with keyboard navigation, and fully clickable file rows without a loading overlay
- Consolidated create-new dropdown replaces separate New File and New Folder buttons
- Inline rename and new-folder creation in the shared footer input row, with modal rename preserved for external callers
- Preserved file tree ancestors — parent folders stay clickable during nested navigation; starting folder is now configurable and defaults to /a0
- Canvas and picker lifecycle fixes — opening a file picker no longer blanks a live canvas listing, and live browsers navigate in place for path links instead of stacking windows
- File permissions and ownership preserved when applying editor patches — executable bits and host-user ownership are no longer replaced with root-owned 0600 files
- Enforced negotiated WebSocket payload ceilings with a symmetric checksummed transfer protocol for large operations, including bounded transfer state, disk spooling, and automatic cancellation on…
- Made workspace HTTP file transfers atomic with streaming uploads into partial files, size verification, fsync, and SHA-256 download receipts
- Bounded remote connector tool payloads with explicit continuation metadata for large content, rejecting oversized inline artifacts before base64 expansion and routing bulk files to authenticated…
- Documented connector payload contracts including WebSocket ceilings, transfer state machine, cancellation lifecycle, and remote text limits
- Added independent, lazily loaded directory trees to Files and Editor in canvas and modal modes with unified styling, lighter panel backgrounds, and flat toolbar controls
- Unified text and code editing in the shared Editor with ACE syntax highlighting, line numbers, native source search, and Markdown preview — removing the legacy file-editor modal
- Context Window Usage Indicator — A bundled plugin showing a composer usage ring, responsive breakdown popover with token counts, percentages, free-space reporting, and provider-reported…
- Context Doctor — Automatically repairs malformed tool-call JSON before dispatch, handles incomplete or thoughts-only responses, supports XML suppression, and persists repaired output in WebUI logs.
- Vision Sidecar Integration — Strict per-preset sidecar slot with Main-first routing, one-call multi-image analysis, parallel-worker image resolution, configurable timeout/max-token controls, and…
- Result Extension Point — Extensions can now normalize or consume completed model results before default history and tool processing.
- WebUI Plugin Slots — New extension slots beside the model/profile strip and at the end of interface visibility controls, allowing plugins to register responsive UI affordances.
- Responses now render with safe Markdown and LaTeX throughout live streaming, removing the raw-to-formatted swap at completion.
Agent Zero popularity and usage data
The GitHub repository has 19.9K stars, 428 of them added in the last 30 days. The latest stable release is 2.16, published Nov 17, 2026; there were 2 stable releases in the past 30 days.
Download the raw daily series: agent-zero.csv
Gid Score breakdown
Gid Score shows public popularity and activity (usage, GitHub stars, mentions, growth), not the quality of the product. Each component is scored 0 to 100 from public signals; a dash means no data for it. How the Gid Score works.
How fresh these numbers are
| Number | Latest reading | Last checked |
|---|---|---|
| GitHub stars | Nov 22, 2026 | Nov 22, 06:26 UTC |
| Website rank (Tranco) | Nov 21, 2026 | Nov 22, 06:27 UTC |
We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.
Agent Zero FAQ
How much does Agent Zero cost?
Free, MIT-licensed open source; you supply your own LLM provider. No pricing page found on the official site.
Is Agent Zero open source?
Yes. Agent Zero is open source, released under the MIT license.
How popular is Agent Zero?
The GitHub repository has 19.9K stars, 428 of them added in the last 30 days. The latest stable release is 2.16, published Nov 17, 2026; there were 2 stable releases in the past 30 days.
What is the latest version of Agent Zero?
The latest stable release we track is 2.16, published on Nov 17, 2026.
What are the alternatives to Agent Zero?
The closest alternatives in the same category by Gid Score are LangChain, LangGraph, AI SDK, Claude Agent SDK.
For the makers of Agent Zero badges, corrections
Add a live badge to your README or site:
[](https://agentgid.com/agents/agent-zero/)
[](https://agentgid.com/agents/agent-zero/)
Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.
Where these numbers come from
GitHub: agent0ai/agent-zero. Site rank: agent-zero.ai on the Tranco list. See data sources for how each one is collected.
Product facts and pricing were checked against: github.com, raw.githubusercontent.com, agent-zero.ai, openrouter.ai.