Open SWE vs SWE-agent
Which should you use? A side-by-side look at what each one does, who it suits, what it costs, how hard it is to set up, and where each falls short.
Open source · MIT
Open-source coding agent that takes engineering tasks and delivers pull requests, meant to be self-hosted.
Open source · MIT
An AI agent that tries to fix GitHub issues automatically, using the language model you choose.
The short answer
Choose Open SWE if you need…
- Engineering teams that want a self-hosted coding agent they can inspect and adapt
- Developers who already run LangChain or LangGraph and want a reference implementation
- Teams that want an agent to handle routine PR work such as reviews and CI follow-ups
- Organizations that need control over sandbox providers, models, and GitHub access
Choose SWE-agent if you need…
- Researchers studying autonomous coding agents or running SWE-bench experiments
- Developers who want to experiment with an LLM attempting issue fixes in their own repositories
- Students learning how agent-computer interfaces work, since the README describes it as simple and hackable
- People who want a configurable agent controlled by a single YAML file
Side-by-side
| Open SWE | SWE-agent | |
|---|---|---|
| Type | AI model / agent | AI model / agent |
| Price | Free and open source | Free and open source |
| Licence | MIT | MIT |
| GitHub stars | 11.2k | 20.7k |
| Setup difficulty | Advanced | Intermediate |
| How you get it | Clone and build from source | Clone and build from source |
| Main language | Python | Python |
| Last code update | 4 days ago | 10 days ago |
What each one is
Open SWE
Open SWE is an open-source coding agent from LangChain that investigates a codebase, makes changes in an isolated sandbox, validates them, and opens a pull request. It can also review pull requests, monitor CI, and respond to feedback. It is built on Deep Agents and LangGraph and is designed to be deployed in your own infrastructure.
SWE-agent
SWE-agent takes a GitHub issue and lets a language model you pick (the README mentions GPT-4o and Claude Sonnet 4 as examples) use tools to try to fix it in a real repository. It is also described as usable for offensive cybersecurity (capture-the-flag) challenges and custom coding tasks. It is a research project from Princeton and Stanford, and its README says its main development has moved to the simpler mini-SWE-agent.
Best for
Open SWE
- Engineering teams that want a self-hosted coding agent they can inspect and adapt
- Developers who already run LangChain or LangGraph and want a reference implementation
- Teams that want an agent to handle routine PR work such as reviews and CI follow-ups
- Organizations that need control over sandbox providers, models, and GitHub access
SWE-agent
- Researchers studying autonomous coding agents or running SWE-bench experiments
- Developers who want to experiment with an LLM attempting issue fixes in their own repositories
- Students learning how agent-computer interfaces work, since the README describes it as simple and hackable
- People who want a configurable agent controlled by a single YAML file
Strengths
Open SWE
- Covers the full loop from investigation to pull request, review, and CI follow-up
- Open source under MIT, and deployable in your own infrastructure
- Lets you choose models, sandbox providers, integrations, and approval policies
SWE-agent
- The README reports state-of-the-art results on SWE-bench among open-source projects
- Configuration is handled by a single YAML file and the README says it is fully documented
- MIT licensed with a public docs site, Slack, and a Codespaces option to try it in a browser
Not ideal for
Open SWE
- Anyone wanting a ready-to-use hosted product: the README says deploying as-is requires Managed Deep Agents, otherwise you must fork and adapt the code to your own runtime
- Teams that expect stable releases: the README says it is under active development with expected breaking changes
- People hoping to contribute issues or patches: the project is not accepting issues or external contributions at this time
- Anyone who needs strong isolation for local execution: the README says local execution does not provide cloud sandbox isolation
SWE-agent
- Teams wanting the project's actively recommended tool: the README says most development has moved to mini-SWE-agent, which it recommends instead
- Anyone needing a polished, finished product: the project is framed as research code
- People who cannot pay for or access a language model API, since the README assumes you bring your own model
Trade-offs
Open SWE
- Under active development with breaking changes and no stability guarantee
- Deployment as-is depends on Managed Deep Agents; otherwise you must adapt it yourself
- Sandboxes have powerful tools and may have network access, so credentials must be tightly scoped
SWE-agent
- The README says mini-SWE-agent has superseded it and is recommended instead going forward
- The EnIGMA cybersecurity mode currently points users to older version 0.7 rather than 1.0
- Results depend on the language model and API you supply; the README does not state costs or hardware needs
Getting started
Open SWE
Clone the repository
git clone https://github.com/langchain-ai/open-sweSWE-agent
Clone the repository
git clone https://github.com/SWE-agent/SWE-agent.gitFrequently asked questions
What is the difference between Open SWE and SWE-agent?
Open SWE: Open-source coding agent that takes engineering tasks and delivers pull requests, meant to be self-hosted. SWE-agent: An AI agent that tries to fix GitHub issues automatically, using the language model you choose. Open SWE suits engineering teams that want a self-hosted coding agent they can inspect and adapt, while SWE-agent suits researchers studying autonomous coding agents or running swe-bench experiments.
Are Open SWE and SWE-agent free?
Open SWE: Free and open source. SWE-agent: Free and open source.
Which is easier to set up, Open SWE or SWE-agent?
SWE-agent is easier to get started with (rated intermediate); Open SWE is rated advanced and usually needs more setup.
Is Open SWE or SWE-agent more popular?
SWE-agent has more GitHub stars (20.7k) than Open SWE (11.2k). Popularity isn't the same as fit — check which one matches your use case above.
What are other alternatives to Open SWE and SWE-agent?
Other options people compare them with include SuperAGI, Hermes Agent, DeerFlow, watermarks-remover, RD-Agent.
Keep comparing
Built from our catalogue entries for both products: open-source details come from each project's README (AI-assisted, refreshed weekly) and GitHub data; AI-tool details are editorial. Spotted something wrong? Let us know from either product's page.