What it does
When software teams change their code, an automatic system called CI/CD (continuous integration and delivery) builds and tests it. When that fails, it says something broke but not why. OpenSRE is an AI agent that runs in the terminal, reads the failed run, looks for the cause and pushes a proposed fix for a person to review.
It gathers logs, recent code changes and other signals, then tests its guesses step by step. Its makers say it can tell failures caused by the CI setup apart from failures caused by the code. It can also post summaries to Slack, PagerDuty or Telegram, and report how much unreliable CI is costing a team.
It can be self-hosted with your own AI models, and it connects to many AI providers, including local ones through Ollama. The README says the project is in public alpha, so it is usable but not yet fully stable.
Who it's for
Software engineers and teams who spend time chasing broken builds and failing tests.
Can I use it without coding?
Developers only. It installs with one command, but using it means working in a terminal with code projects and build systems. New to this? Start here.
Can I run it?
- Runs on
- Mac, Windows, Linux, Server, Cloud
- Computer
- An ordinary computer is fine
- Privacy
- Your choice: run it on your device or use an online service
Try it
- Open a terminal inside a code project, ideally a Git repository.
- Run the one-line installer for your system from the README.
- Start OpenSRE and sign in when asked, then describe the problem in plain language.
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- Plain-AyI is an independent guide and doesn't host or review the software it lists. Please check each project's official page before installing.
- License (Apache-2.0): Permissive: free to use, change and share, including for business.
- More on staying safe
Where people are talking about it
- SWE-bench: Can Language Models Resolve Real-World GitHub Issues?Research paper · Oct 2023