Home/OpenHands
OpenHands logo

OpenHands

OpenHands is a model-agnostic coding-agent platform for implementing features, fixing bugs, maintaining repositories, and automating engineering work locally, in the cloud, or in a private deployment.

Visit website
OpenHands autonomous coding agent platform

Product overview

What is OpenHands?

OpenHands is an open platform for autonomous software-development agents. It can work with repositories to implement features, fix bugs and tests, resolve merge conflicts, address review feedback, and handle recurring maintenance. Developers can use a local GUI, terminal interface, CLI, software-agent SDK, hosted cloud service, or enterprise deployment.

The core OpenHands software is MIT licensed and model agnostic. Cloud and enterprise offerings add hosted runtimes, APIs, collaboration, integrations, access controls, and private deployment options. Agents execute code in isolated runtimes, but generated changes still require review and testing before they reach production.

How to Use OpenHands

  1. Choose local, hosted cloud, or enterprise deployment based on privacy and collaboration needs.
  2. Connect a Git provider or open a repository in the local environment.
  3. Configure a supported language model through your own key or the available provider.
  4. Describe a concrete engineering task and let the agent inspect and modify the codebase.
  5. Review the diff, run project checks, and approve only verified changes.

Core Features

  • Autonomous coding agent: Works through multi-step repository tasks rather than only suggesting snippets.
  • Model-agnostic operation: Supports user-selected language-model providers and bring-your-own-key access.
  • Multiple interfaces: Provides web GUI, terminal UI, CLI, API, and SDK workflows.
  • Git integrations: Connects with GitHub, GitLab, and Bitbucket for repository tasks.
  • Cloud parallelism: Runs multiple hosted conversations without managing local infrastructure.
  • Enterprise controls: Adds private deployment, SAML or SSO, RBAC, centralized billing, and support.

Use Cases

  • Bug fixing: Agents can investigate failures, edit code, and propose tested fixes.
  • Feature implementation: Engineering teams can delegate bounded issues and review the resulting pull-request changes.
  • Repository maintenance: OpenHands can address tests, merge conflicts, routine upgrades, and review comments.
  • Custom coding agents: Developers can build specialized workflows with the SDK and API.

Pricing

OpenHands Local is open source and free to run, with users paying for their own model usage and compute. The hosted Individual tier is free for one user, supports bring-your-own-key or OpenHands models billed at provider cost, and currently limits daily cloud conversations. Enterprise is custom priced and can run as SaaS or inside a private environment with multi-user administration and support.

Frequently Asked Questions

Is OpenHands open source?

The core OpenHands project, local GUI, CLI, and software-agent SDK are MIT licensed. Some cloud and enterprise capabilities use separate commercial terms.

Can teams use their own model keys?

Yes. Local, cloud, and enterprise options support bring-your-own-model credentials.

Does OpenHands replace code review?

No. It can execute and propose substantial engineering work, but teams should inspect changes and run the repository's tests, security checks, and deployment controls.

Back to product directory

Related products

OpenAI Codex is an AI coding product for delegating scoped repository tasks and reviewing the resulting changes.

Claude Code is Anthropic’s AI coding product for iterative repository work through supported development surfaces.

Gemini CLI is Google’s open-source AI agent for terminal workflows and local development tasks.

Newsletter

Keep up with useful AI products

Get a concise selection of new products, practical use cases, and builder updates.