OpenHands
A self-hosted control panel that runs AI coding agents on your machine, in Docker, or in the cloud.
- Stars
- 92.5k
- Forks
- 12.3k
- Licence
- MIT
- Language
- TypeScript
- Last update
- 4 days ago
- Type
- App
What it is
Agent Canvas is a self-hosted control center for AI coding agents. You start conversations with agents and set up automations, such as generating reports that publish to Slack or breaking GitHub issues into tasks. It runs on your own machine by default and can also connect to agents running in Docker, on virtual machines, or on OpenHands Cloud or Enterprise infrastructure. It can run the open source OpenHands agent or third-party agents such as Claude Code, Codex, and Gemini CLI.
- Start a coding conversation with an agent against a project folder on your machine
- Run agents in separate Docker containers so several conversations can run at once
- Create automations that run on a schedule or respond to webhook events
- Connect automations to Slack, GitHub, Notion, or Linear to move work between tools
Great for
- Developers who want coding agents running on a server while their laptop is off
- Teams that want a shared agent server for tasks like code review or dependency updates
- People who want to connect agents to Slack, GitHub, or Linear through automations
- Users who want to choose their own LLM provider
Not ideal for
- People who need strong isolation by default: the quickstart without a sandbox gives the agent full access to your filesystem
- Non-technical users who are not comfortable with Node.js, npm, Docker, or the command line
- Anyone who needs a fully hosted service with no setup, since the README centers on self-hosting
How to get it
- 1
Install with a package manager
You'll need: Node.js 24 or later · uv · Docker (optional, for sandboxed options)
Install globally with npm (no sandbox)
npm install -g @openhands/agent-canvasStart the full local stack
agent-canvasRun each conversation in its own Docker container
OH_CONVERSATION_RUNTIME=docker agent-canvas - 2
Run it
- Install Node.js 24 or later and uv
- Run npm install -g @openhands/agent-canvas
- Run agent-canvas to start the local stack
- Open http://localhost:8000 in your browser and start a new conversation
- 3
Get the most out of it
- Use the Docker sandbox options so the agent only accesses the project folders you mount
- Run agents on a remote server or in the cloud so they keep working when your laptop is shut
- Set up automations to publish reports to Slack or decompose GitHub issues into tasks
- Configure multiple LLM profiles to use different models (see the LLM settings docs)
- Use separate directories or git worktrees for concurrent conversations to avoid conflicting edits
Downloads
Strengths
- Self-hosted, so you control where agents run and where your work is stored
- Supports several agents and backends from one frontend
- Released under the MIT license with a large public community (about 92,000 stars)
Trade-offs
- Running without a sandbox gives the agent full access to your filesystem, so the Docker options need careful setup
- Multiple features depend on configuring backends, LLM keys, and integrations, which takes effort
- The README is truncated and does not fully document security hardening or every integration; see the linked docs
How it compares
| Project | Stars | Type | Level | Updated | Best for |
|---|---|---|---|---|---|
| OpenHands (this) | 92.5k | App | intermediate | 4 days ago | Developers who want coding agents running on a server while their laptop is off |
| repomix | 29.1k | CLI | beginner | 4 days ago | Developers who want to ask an AI assistant questions about a whole project |
| botpress | 15k | Dev tool | intermediate | 6 days ago | Developers who want to write integrations and bots as TypeScript code using the Botpress CLI and SDK |
| one-api | 37.3k | App | intermediate | 10 months ago | Developers who want one OpenAI-compatible endpoint for several model providers |
| generative-ai-for-beginners | 123k | Learning resource | beginner | 5 days ago | Developers who know some Python or TypeScript and want a guided introduction to generative AI |
| Prompt-Engineering-Guide | 79.8k | Learning resource | beginner | 8 months ago | People who are new to prompting and want structured lessons with examples |
Stats synced from GitHub. The assessment above was drafted with AI from the project's README on 2026-10-29 and may miss recent changes — check the README before relying on a command. MIT licence: free to use, modify and distribute, including commercially, as long as you keep the copyright notice.