Agent Zero
Open-source autonomous AI agent with its own Linux workspace in Docker that researches, writes and runs code, and works with documents through a terminal, browser and desktop apps, using a model you connect.
About Agent Zero
General-purpose AI agents either run in someone else's cloud or need direct access to your computer, which makes long autonomous tasks hard to inspect and contain.
Who it’s for
- Technical users who want a self-hosted general agent that can use a full Linux computer
- Developers who want to extend an agent framework with their own tools and model providers
When to consider it
Consider Agent Zero when you want a self-hosted, MIT-licensed agent that runs sandboxed in Docker, can be set up with a desktop launcher or one install command, and lets you step in or connect local files when needed.
Tradeoffs & limitations
- You must bring a supported AI account, a provider API key or a local model server, and Docker is required (the A0 Launcher helps set it up).
- Remote deployments need you to configure access and authentication yourself; the Web UI is bound to the Docker host by default.
SOTA overview · Documentation-based assessment · Sources & review method
Updates
No updates shared yet.
Discussion
Newest firstAsk a question or share how you use Agent Zero.
Keep it helpful. Community rules
Loading discussion…
Sources & review method
Documentation-based assessment · Nov 2, 2026 · Prepared with AI assistance; not a hands-on benchmark.
Checked by SOTA · AI-assisted documentation review. Selection advice is our assessment; verify current requirements for your deployment.
Import history & original evidence
Agent Zero official website
Open-source autonomous AI agent with its own Linux workspace in Docker that researches, writes and runs code, and works with documents through a terminal, browser and desktop apps, using a model you connect.
Based on official pages and announcements checked on 2026-11-02. No hands-on test, performance benchmark or popularity ranking is claimed.