An Open-Source Asynchronous Coding Agent
Find a file
2025-07-29 14:37:31 -07:00
.github/workflows fix: Auto sync docs workflow conditional, sync images too (#590) 2025-07-29 11:29:57 -07:00
.vscode Brace/07 16/fixes (#431) 2025-07-16 13:17:35 -07:00
apps fix: Dont filter bot comments when updating bot comment (#597) 2025-07-29 14:37:31 -07:00
packages/shared feat: add updates to cli application (#503) 2025-07-29 17:37:13 -04:00
static fix: Cleanup readme, small changes to docs (#458) 2025-07-21 21:12:55 +00:00
.codespellignore init commit 2025-05-21 14:47:56 -07:00
.gitignore feat: Monorepo (#22) 2025-05-26 13:02:51 -07:00
.yarnrc.yml feat: Monorepo (#22) 2025-05-26 13:02:51 -07:00
AGENTS.md [open-swe] feat: Add AGENTS.md with development guidelines and repository context (#303) 2025-06-23 21:58:49 +00:00
langgraph.json feat: trigger runs from GH issues (#324) 2025-06-30 16:43:09 -06:00
LICENSE feat: Monorepo (#22) 2025-05-26 13:02:51 -07:00
package.json fix: running tests and in ci (#536) 2025-07-27 19:11:34 +00:00
README.md feat: Add Max Mode Labels with Claude Opus 4 Support (#577) 2025-07-28 16:33:12 -07:00
SECURITY.md fix: Security stuff (#441) 2025-07-17 12:19:20 -07:00
tsconfig.json chore: Add CI job which runs the dev server (#61) 2025-05-30 13:54:44 -07:00
turbo.json fix: running tests and in ci (#536) 2025-07-27 19:11:34 +00:00
yarn.lock feat: add updates to cli application (#503) 2025-07-29 17:37:13 -04:00

Warning

Open SWE is under active development and is not yet ready for production use.

Open SWE Logo

Open SWE - A cloud based, fully autonomous coding agent

Open SWE is an open-source cloud-based coding agent built with LangGraph. It autonomously understands codebases, plans solutions, and executes code changes across entire repositories—from initial planning to opening pull requests.

Tip

Try out Open SWE yourself using our public demo!

Note: you're required to set your own LLM API keys to use the demo.

Features

  • 📝 Planning: Open SWE has a dedicated planning step which allows it to deeply understand complex codebases and nuanced tasks. You're also given the ability to accept, edit, or reject the proposed plan before it's executed.
  • 🤝 Human in the loop: With Open SWE, you can send it messages while it's running (both during the planning and execution steps). This allows for giving real time feedback and instructions without having to interrupt the process.
  • 🏃 Parallel Execution: You can run as many Open SWE tasks as you want in parallel! Since it runs in a sandbox environment in the cloud, you're not limited by the number of tasks you can run at once.
  • 🧑‍💻 End to end task management: Open SWE will automatically create GitHub issues for tasks, and create pull requests which will close the issue when implementation is complete.

UI Screenshot

Usage

Open SWE can be used in multiple ways:

  • 🖥️ From the UI. You can create, manage and execute Open SWE tasks from the web application. See the 'From the UI' page in the docs for more information.
  • 📝 From GitHub. You can start Open SWE tasks directly from GitHub issues simply by adding a label open-swe, or open-swe-auto (adding -auto will cause Open SWE to automatically accept the plan, requiring no intervention from you). For enhanced performance on complex tasks, use open-swe-max or open-swe-max-auto labels which utilize Claude Opus 4 for both planning and programming. See the 'From GitHub' page in the docs for more information.

Documentation

To get started using Open SWE locally, see the documentation here.