Skip to content
  1. Home
  2. AI tools
  3. OpenHands

OpenHands

Self-hosted control center for running and automating coding agents

What it is

A self-hosted platform for running coding agents and scheduled automations. The current README centres on Agent Canvas, a control surface that can drive OpenHands' own agent or other ACP-compatible agents across local, Docker, VM and cloud backends. For teams that want agents running continuously on their own infrastructure.

Good for

  • Run several coding agents from one dashboard
  • Automate turning GitHub issues into tasks
  • Run agents inside Docker or on remote machines

Install or run

npm install -g @openhands/agent-canvas

Command as given in the project README. Read the repository before you run anything on your machine.

What you need

Node.js or Docker; LLM provider credentials for the agents you run

Worth knowingThe project has shifted focus from a single coding agent to the Agent Canvas control center, so older tutorials may not match.

Sources

The summary is ours, written from the README. Spotted an error? See how we work.

More for coding

See the topic →
  • opencode

    anomalyco/opencode

    Open-source AI coding agent with a terminal UI and desktop app

    ToolGitHub stars: 227k
  • Claude Code

    anthropics/claude-code

    Anthropic's terminal coding agent; this repo hosts issues and plugins

    ToolGitHub stars: 156k
  • Spec Kit

    github/spec-kit

    GitHub's toolkit for spec-driven development with coding agents

    ToolGitHub stars: 150k
  • Codex CLI

    openai/codex

    OpenAI's terminal coding agent that runs locally on your machine

    ToolGitHub stars: 135k