Agent Zero
Docker-packaged autonomous agent with a web UI, code execution, sub-agents, and prompt-defined behavior.
About
Rather than a coding SDK, Agent Zero is a ready-to-run autonomous agent operated through a web UI, with the whole runtime packaged as a Docker container that now ships a full XFCE Linux desktop the agent can drive. Inside that sandbox it writes and executes code, browses with DOM annotation, edits documents in LibreOffice, and spawns subordinate agents that hand results back up the chain, while persistent memory carries knowledge and learned skills across sessions. Behavior lives in editable prompt files rather than hardcoded logic, so the agent's persona, tools, and workflow can be rewritten without touching source, and a plugin hub with over 100 community extensions plus MCP support covers integrations. Setup is a single docker run command or the A0 Launcher desktop app; projects isolate memory and secrets per workspace, and snapshot-based time travel rolls a broken workspace back. MIT licensed and free with about 19k GitHub stars, it connects to hosted providers, OpenRouter, or local models through Ollama.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- AI Agents & Orchestration
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Easy (2/5)
- License
- MIT
- Added
- Aug 24, 2026
Related Tools
Multi-agent framework for building and studying societies of communicating LLM agents at scale.
Super-agent harness orchestrating sub-agents, memory, and sandboxes for research and automation.
TypeScript agentic operating system with plugins, memory, and connectors for major messaging platforms.
Code-first, model-agnostic toolkit for building, evaluating, and deploying AI agents.
Autonomous agent that plans queries, searches the web and local files, and writes cited reports.
Platform for building and running autonomous agents that execute complete workflows from goals.