OpenSRE
OpenSRE is a command-line agent that investigates failed CI builds and pushes a proposed fix for engineering teams to review.
What it is good for
- Finding out why a CI build keeps failing
- Fixing a red main branch without manual log digging
- Telling flaky checks apart from real code bugs
- Investigating production incidents using logs, metrics, and recent deploys
At a glance
- Who it is for
- Setup difficulty
- Technical ยท Guided command-line setup
Level 4 of 5. You copy and paste commands into a terminal by following the instructions. Comfortable territory for vibe coders.
- Cost
- Not stated
- Type
- Agent app
- Tasks
- Works with
- Slack, PagerDuty, Telegram, Datadog, Grafana, GitLab CI
How to get started with OpenSRE
- Open a terminal inside your code project, ideally a Git repository.
- Run the install command for your system from the README (macOS or Linux, or Windows PowerShell).
- Start the agent by running
opensre. - Sign in on first launch, which activates the hosted model.
- Describe an incident in plain language, or run
opensre askwith a question for a one-off answer.
From the project's own documentation. If a step does not match what you see, the official pages have the latest instructions.
Before you try it
- It is in public alpha, so core workflows work but APIs and integrations may change.
- You need a terminal and the install script fetches the latest build from main.
- The interactive shell only opens for an active signed-in account.
- Optional masking of sensitive identifiers applies before calls to external language models.
Momentum
- Rank this week
- Not ranked yet
- Best rank
- None yet
- GitHub stars
- 12,835
GitHub numbers as of Nov 16, 2026. Updated weekly.
Official links
Questions
- Do I need to know how to code to use OpenSRE?
- You do not need to write code, but setup means copying and pasting commands into a terminal by following its instructions.
- What does OpenSRE work with?
- According to its own documentation, it works with Slack, PagerDuty, Telegram, Datadog, Grafana, and GitLab CI.
- How do I get started with OpenSRE?
- 1. Open a terminal inside your code project, ideally a Git repository. 2. Run the install command for your system from the README (macOS or Linux, or Windows PowerShell). 3. Start the agent by running opensre. 4. Sign in on first launch, which activates the hosted model. 5. Describe an incident in plain language, or run opensre ask with a question for a one-off answer.
- What should I know before trying OpenSRE?
- It is in public alpha, so core workflows work but APIs and integrations may change. You need a terminal and the install script fetches the latest build from main. The interactive shell only opens for an active signed-in account. Optional masking of sensitive identifiers applies before calls to external language models.
- What is OpenSRE good for?
- Finding out why a CI build keeps failing, fixing a red main branch without manual log digging, telling flaky checks apart from real code bugs, and investigating production incidents using logs, metrics, and recent deploys.
Similar agents to OpenSRE
- OpenHands
Focuses on running coding agents generally, not on investigating failed CI runs and incidents.
- Archon
Runs coding agents through fixed YAML workflows rather than investigating CI failures and alerts on its own.
- CompanyOS
Runs always-on company agents from schedules and webhooks, not specialized for CI and incident diagnosis.
- goose
General-purpose local agent for coding and automation, with no focus on CI reliability.
- Cline
Writes and edits code in your editor, rather than diagnosing failed builds and alerts.
- AgentRun
AgentRun is an agent app that cuts repeat token costs and recovers interrupted runs by letting agents learn jobs, for teams running agents.