Open-source desktop app to run, serve and fine-tune text, image, video and audio models entirely on your own machine.
Summary
OpenHands — the leading open-source coding agent platform, self-hostable or run in the cloud.
Screenshots
Description
OpenHands is an open-source platform for AI software agents, and one of the most-starred projects in the space. Its agents do what a developer does: modify code, run commands, browse the web, call APIs, and yes, copy a snippet from Stack Overflow when that is the right answer.
What you get
- A sandboxed runtime. Each agent session runs in a container with a real shell, a browser, and a Jupyter kernel, so it can execute and verify its own work.
- Model agnosticism. Use any major provider or a local model — nothing is hard-wired to one vendor.
- Multiple entry points. A web UI, a CLI, a GitHub Action that resolves issues, and a headless mode for scripted use.
- Microagents. Repository-specific instructions that teach the agent your conventions and are checked into the repo.
- Self-hosting. Run the whole thing with Docker on your own infrastructure, which matters when code cannot leave the building.
Options
The open-source project is free under the MIT licence. All Hands also offers a managed cloud with the same agent, for teams that would rather not operate it. A strong default if you want agentic coding without vendor lock-in.
Reviews
Similar App Suggestions
Spotify's vendor-neutral workspace for running dozens of Claude Code, Codex and Gemini CLI sessions in parallel with shared context.
A coding agent tuned for latency: routes easy work to fast models, pulls only the code it needs, and fans out tool calls in parallel.
Run agent evals and private benchmarks in sandboxed cloud environments — compare Claude Code, Codex, Cursor and Copilot on the same real tasks.
An open-source proxy that sits between your coding agent and the model, compressing tool schemas, file reads and stale history to cut token bills.