Skip to content
Agents tracked: 271 Downloads (7d): 219M up 6.1% GitHub stars: 5.5M VS Code installs: 151M Releases (7d): 291 Agent status: 2 with issues Updated Oct 8, 2026

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.

Agent frameworks and SDKs New · Added to AgentGid on Oct 8, 2026Open-source autonomous agent frameworkOpen source · MITFree to start
Price
Free (OSS)
free and open source
Popularity
#30 in Frameworks
Gid Score 21 / 100 · #171 of 271 overall
Trend
Gaining stars
about +8 GitHub stars a day
Development
Actively updated
latest 2.13, 15d ago
Community
19.4K GitHub stars
public signals

What Agent Zero does

Key facts

MakerAgent Zero s.r.o.
TypeOpen-source autonomous agent framework
LicenseMIT
InterfacesWeb app, CLI, Desktop app
Main languagePython
Open issues and PRs141

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.

Compare prices of all agents

Quick answers

  • Free to start?Yes
  • Open source?Yes (MIT)
  • Where you use itWeb app, CLI, Desktop app
  • Closest alternativeLangChain · all alternatives

Get started with Agent Zero

Setup instructions are in the official documentation.

Compare Agent Zero with another agent

vs
# Agent Gid Score Downloads 7d 7d 30d VS Code installs Stars Latest release Price
4
LangChainLangChain
77 43.7M down 0.7% down 20.2% — 148K+43/day 1.4.310d ago Free (OSS)
10
LangGraphLangChain
69 16.1M up 7.9% down 18.1% — 42.8K+49/day 1.2.142d ago Free (OSS)
11
AI SDKVercel
67 34.4M up 8.8% up 25.2% — 27.2K+19/day 7.0.131yesterday Free (OSS)
12 63 8.7M down 0.7% up 4.0% — 8,722+20/day 1.58.12d ago Free (OSS)
19 60 21.5M up 10.2% up 2.7% — 8,219+5/day 0.2.1642d ago Free (OSS)
22
MastraMastra
59 2.3M up 9.2% up 24.3% — 28.6K+26/day 1.75.0yesterday Free (OSS)

Agent Zero news

All AI agent news

  1. New on AgentGid AgentGid

    13 agents added to AgentGid

    CodeGPT, Traycer, Command Code, Lemonade, Vellum, Agent Zero, ZCode, openJiuwen, Do Browser, PostQode, Ito, Mira and 1 more

What changed: recent Agent Zero releases

10 stable releases in the last 90 days · Full changelog

2.13
  • 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
2.12
  • 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
2.11
  • 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…
  • 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. Repeat detection and empty-response handling are split into…
  • 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.
2.10
  • Interactive viewport: The internal Browser now renders a live, interactive session via Xpra with CDP screencast and snapshot fallbacks, replacing static screenshot-only interaction.
  • Shared runtime: All chats route through a single persistent Chromium, Xvfb, and Xpra instance. Sign-ins are shared across chats while tab ownership and limits remain per-chat.
  • Bot detection hardening: Chromium now runs headful through Patchright on a private Xvfb display, significantly improving resilience against bot detection.
  • Tab restore: Browser tabs are automatically persisted and restored per-chat and in shared scopes, without showing Chromium's crash advisory on restart.
  • Browser model preset: The configured Browser model preset is now correctly activated after the first Browser tool call and cleared at monologue end.
  • Annotation and UI improvements: Added DOM hover feedback, multi-page annotation batches, compact composer-style controls, and microphone/arrow controls in the annotation dialog.
2.9
  • New Agent Editor UI with Easy and Advanced modes for editing agent identity, prompts, model presets, tool policies, skill visibility, and avatars — all without destructive overwrites or model calls.
  • Project-scoped profiles: switch between Global and project scope when managing agents; sparse reads, writes, resets, and policy configs stay bound to the selected layer.
  • Profile lifecycle management: per-scope availability, duplication, active-profile status, inline project selection, scoped restore for inherited profiles, and synchronized profile switching across…
  • Reusable profile commands: create profiles quickly via /profile in chat or through the Connector API, then open a fresh chat with the new profile in the selected scope.
  • /permissions slash command: opens the current profile's Agent Editor directly from chat.
  • Tools, MCPs, and Skills get explicit default switches with segmented per-item policy controls, preserving sparse overrides.
2.8
  • Stop button and /stop API — Cancel a running agent context without deleting it. The chat bar now shows a stop button while the agent is working, and a new /stop endpoint is available for…
  • UI asset bundler and service worker — A new build-time bundler discovers same-origin HTML, CSS, and JS assets and delivers them as a versioned JSON bundle. A service worker pre-populates a…
  • WebUI extension manifest — The bundler and server now support an extension manifest, allowing enabled extensions to inject their own entry files into the bundle. The index page is rendered with…
  • Chat-naming and pin-to-top plugins — Chat renaming has been extracted from core into a dedicated chatnaming plugin with its own API, prompts, UI modal, and Utility Model integration. A new…
  • Lazy chat rendering and pagination — messages.js has been refactored to support lazy rendering of chat messages, improving performance for long conversations.
  • Slash commands exposed through skills — The Commands plugin now handles scoped command discovery, and the skills tool can list or read effective slash-command definitions without invoking them. A…

Agent Zero popularity and usage data

The GitHub repository has 19.4K stars, 333 of them added in the last 30 days. The latest stable release is 2.13, published Sep 23, 2026; there were 2 stable releases in the past 30 days.

GitHub starsrunning total 19.4K
Website rankTranco list; a lower rank means more traffic #1,461,516

Download the raw daily series: agent-zero.csv

Gid Score breakdown

Adoption0
Community54
Attention—
Momentum51

Each component is scored 0 to 100 from public signals; a dash means no data for it. Methodology.

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 19.4K stars, 333 of them added in the last 30 days. The latest stable release is 2.13, published Sep 23, 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 2.13, published on Sep 23, 2026.

What are the alternatives to Agent Zero?

The closest alternatives in the same category by Gid Score are LangChain, LangGraph, AI SDK, Strands Agents.

For the makers of Agent Zero badges, corrections

Add a live badge to your README or site:

AgentGid: #30 in Frameworks Gid Score: 21/100

[![AgentGid: #30 in Frameworks](https://agentgid.com/badges/agent-zero-rank.svg)](https://agentgid.com/agents/agent-zero/)
[![Gid Score: 21/100](https://agentgid.com/badges/agent-zero-score.svg)](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.