Verified project record

OpenHands/OpenHands

OpenHands is a self-hosted developer control center for starting, managing, and automating coding agents across various local and remote environments. It supports running agents in Docker, on VMs, in the cloud, or locally, and allows developers to use any LLM.

Project overview

The project provides a centralized interface for orchestrating coding agents across multiple execution backends without losing focus.

Project type: AI Agent · AI Coding
Use cases: Coding & Development · Automation
Deployment: Refer to project documentation
License: MIT

Best for

Developers who need a self-hosted control center to manage and automate coding agents across various execution backends.
Teams looking to integrate coding agents with platforms such as Slack, GitHub, or Linear.

Key capabilities

Run coding agents locally, in Docker, on VMs, or in the cloud, switching between backends without losing focus.
Use any LLM with the coding agents.

Limitations and risks

Running the agent server directly without a Docker sandbox gives the agent full access to your filesystem.
Running without a sandbox means the agent will have full access to your filesystem.
The data boundary is external optional, and paid services may be optionally required, indicating that cloud round-trips or external LLM APIs may be used during operation. Telemetry is not documented.

Getting started

Installation is rated as easy. Users can install and run the application via a single npm command or Docker container without needing to write code. The first success path involves installing the npm package globally, running the agent-canvas command, and accessing the UI at localhost:8000.

Alternatives and comparisons

Provides a unified multi-provider LLM API, an agent runtime with tool calling, and an interactive coding agent CLI with a terminal UI.
Opinionated plugin and CLI providing an out-of-the-box multi-agent orchestration harness with automated model routing, context injection, and reliable code editing tools.
Small, composable, and adaptable engineering skills for AI coding agents that enforce software engineering fundamentals.

Project comparisons

Evidence and sources

README: status-beta-blue
README: It's a developer control center for starting conversations and automating everyday tasks
README: Switch between local, remote, and cloud agents without losing focus
README: Create automations and workflows that integrate with Slack, GitHub, Linear, and more. Run on a schedule or in response to webhook events
README: Use with OpenHands, Claude Code, Codex, Gemini, or any agent with Agent-Client Protocol (ACP).

Source updated at: 2026-07-16T18:19:59Z

Open original GitHub project