
OpenHands is a coding agent platform for developers and teams that want agents to make changes across a codebase and handle recurring engineering work. You can run it on your own computer or self-host it on a server. Its core is open source under the MIT license, and a separate OpenHands Cloud service offers hosted execution.
Agents can investigate issues, edit code, run checks and prepare pull requests. OpenHands also supports workflows triggered by repository activity, schedules and tools such as GitHub, Slack, Jira and Linear. That makes it useful for work that starts outside an editor, including pull request reviews, CI failures, issue triage and documentation updates. Engineers retain control over review, approval and merge.
The platform isn't tied to one coding agent or model. It can run the OpenHands agent alongside Claude Code, Codex, Gemini CLI and compatible third-party agents. It works with closed models and open-weight models such as Kimi, DeepSeek and Qwen, with execution on a local machine, a VM or infrastructure controlled by an organization. Docker-based local setups are documented for macOS, Windows and Linux. MCP connections let agents use internal tools and data sources.
For teams, the shared control center brings conversations and automations together across repositories. Agents can work in isolated environments, and organizations can control access and audit their actions. Self-hosting gives an organization control over agent execution and workspace storage. Calls to hosted model providers still send their inputs to those services. OpenHands Cloud runs agents on the hosted service.
Claim this page with an email at all-hands.dev. OpenHands gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find OpenHands?Promote it
Something wrong or outdated on this page?
127.2KUpdated 24 hours agoApache-2.0
macOS · Windows · Linux#Code execution#Git integration#Human approval
Codex CLI is an open source coding assistant that runs on your computer and works with local repositories. It's for developers who want to explore code, make changes, and use their existing development tools from the terminal. It runs on macOS, Windows, and Linux under the Apache 2.0 license.
4.8KUpdated 1 day ago
Docker · Web#Git integration#Human approval#LLM tracing
Agenta is an MIT-licensed, open source workspace for teams that want AI agents to handle tasks in chat and continue recurring work in the background. You can self-host it with Docker Compose or Helm to keep agents and workspace data on your infrastructure, or use Agenta Cloud as a hosted service.
293KUpdated 5 days agoMIT
Windows#Agent Skills#Code execution#Git integration
269.7KUpdated 20 hours agoMIT
Windows#Guardrails#MCP#Multi-agent workflows
27.5KUpdated 35 minutes agoMIT
VS Code · JetBrains#Code execution#Git integration#MCP
272.1KUpdated 1 day agoMIT
#Agent Skills#Git integration#Multi-agent workflows
Superpowers adds a structured development process to AI coding assistants. It's for developers who want their agent to agree on a design before writing code, follow an implementation plan, and check its work against that plan. The open-source framework uses the MIT license and works inside coding tools including Claude Code, Codex, Cursor, Gemini CLI and OpenCode.
ECC is a free, MIT-licensed open source toolkit that adds repeatable engineering workflows to coding assistants. It runs alongside your chosen agent and works with self-hosted models or cloud providers through that agent's supported endpoints. It's for developers who want planning, testing and review to follow a consistent process across coding sessions.
Kilo Code is an AI coding agent for developers who want help writing and understanding code in their editor or terminal. It runs in VS Code, JetBrains IDEs and the CLI, with cloud agents available for remote work. The project is open source under the MIT license and can be self-hosted.
Skills (mattpocock) is an MIT-licensed collection of engineering workflows for developers using Claude Code, Codex and other AI coding agents. Its small, separate skills work with any model and can be combined or adapted to your project, so you can choose specific practices without adopting an entire development process.