The Claude Code background agent for Linear, Slack, Github, GitLab etc. you deploy anywhere. Supports Codex, Cursor and Gemini too.
C-Rank Grade: B (Solid) - 47/100
External PR Merge Rate: 53%
Response Time: 8d
First Timer Success: 25%
cyrusagents/cyrus has a recorded first-timer success rate of 25.0%. Repositories ranked B typically provide actionable feedback during code reviews and actively nurture new community contributors.
Maintainers in cyrusagents/cyrus respond to incoming external pull requests in approximately 185.4 hours on average. Keeping PRs focused on single tasks and ensuring tests pass helps maintainers review faster.
The C-Rank™ system evaluates GitHub projects on a 0–100 scale using real data: PR merge rates, review turnaround time, active maintainer presence, and first-time contributor success. A score of 47.0 places cyrusagents/cyrus in the B tier.
The external contributor pull request merge rate for cyrusagents/cyrus is 52.8%, based on public PR activity from non-core contributors.
cyrusagents/cyrus currently has 3 active issue(s) tagged with beginner-friendly labels like "good first issue", "beginner", or "up-for-grabs".
The Claude Code background agent for Linear, Slack, Github, GitLab etc. you deploy anywhere. Supports Codex, Cursor and Gemini too.
Rigorous architecture standards (100% critical review signals). Ensure PRs strictly follow guidelines before requesting review in cyrusagents/cyrus.
Average Response Latency
Tracks hours until a maintainer leaves a review, comment, or PR response.
External Acceptance Rate
Percentage of community pull requests successfully merged into main.
First PR Conversion
Rate at which developers submitting their first repository PR succeed.
Show contributors that your repository actively reviews and merges external pull requests.
[](https://getmerged.abhishekco.de/cyrusagents/cyrus?utm_source=github&utm_medium=badge)
Historical health & responsiveness evolution
External PR acceptance
First PR success rate
50% receive response in
90% receive response in
Maintainer review activity heatmap & prime window prediction
Calculating local time...
Calculating local time...
Detected: UTC
Maintainers are most responsive around 15:00 UTC (15:00 UTC in your timezone). Recommended submission window is Monday - Thursday from 13:00 to 17:00 UTC (13:00 - 17:00 UTC local).
Limited recent maintainer review activity recorded for this repository. Prediction based on heuristic baseline.
Maintainer Strategy: Maintainer Sweet Spot: PRs under 150 lines merge in ~120 hours (66% approval). Large PRs (>500 lines) take ~890 hours (24% approval). Keep your diff compact for rapid review.
Enter your branch size and test coverage below to forecast review turnaround and get 1-click git splitting commands.
Alternative open-source projects with active maintainers in TypeScript.
AI-powered cross-platform e-book reader with semantic search, RAG chat, local vector store, notes, TTS, and WebDAV sync.
Set of Angular challenges to practise and train on Angular
email infrastructure for agent and indie devs
Summary Cyrus does not currently parse OpenCode usage, cost and finish-reason information from the event fields where OpenCode emits them. Current behavior Cyrus reads these values from the top level of a step_finish event. OpenCode's current event shape places them inside step_finish.part, causing Cyrus to record missing or inaccurate session accounting. Expected behavior Cyrus should parse the current OpenCode event shape and record usage, cost and finish reason accurately. Why this matters Incorrect accounting makes OpenCode sessions harder to observe and can produce inaccurate usage and cost reporting. Acceptance criteria Usage is read from the current step_finish.part fields. Cost is recorded accurately. The actual finish reason is preserved. Missing optional values are handled safely. A single event is not counted more than once. Top-level fields can remain as a backwards-compatible fallback if needed. Test fixtures reflect real OpenCode JSON output. Validation Add tests using
Summary Cyrus-managed skills are not currently made available to OpenCode sessions. Current behavior Cyrus passes managed-skill information through the shared runner configuration, but the OpenCode runner does not install or expose those skills. OpenCode can use its own configured skills, but it cannot discover the Cyrus-managed skills available through other runners. Expected behavior Skills enabled by Cyrus should be discoverable and usable in OpenCode sessions under the same intended policy. Why this matters OpenCode sessions currently behave differently from other Cyrus runners when a workflow depends on a managed skill. Acceptance criteria Skills enabled for the session are available to OpenCode. Skills not enabled for the session remain unavailable. Existing OpenCode user and project skills continue working. Cyrus does not overwrite unrelated OpenCode configuration. Skills work with both shared and isolated OpenCode state. Cyrus reports the skills actually available to the sessi
Summary OpenCode sessions do not currently support steering of an active turn. Current behavior When a user sends an immediate steering message while OpenCode is running, Cyrus stops the OpenCode process and resumes the session with the new message. OpenCodeRunner reports that it does not support streaming input, and attempting to send a streaming message throws an error. Expected behavior A steering message should affect the currently running turn without stopping it or starting a replacement turn. A server-backed OpenCode session may be the right foundation, but the implementation does not need to be prescribed here. Why this matters Users are told they can steer active work, but with OpenCode that action currently interrupts the work instead. Acceptance criteria Steering reaches the active OpenCode session without stopping it. The running turn can incorporate the new instruction before completing. The OpenCode session and its context are preserved. Cyrus does not report that the se
Rate what actually matters after opening a pull request here.
Rate your first-hand PR experience (review speed, maintainer responsiveness, and onboarding ease) to help other contributors.
When evaluating whether to contribute to cyrusagents/cyrus, response velocity and maintainer engagement are crucial. GetMerged continuously tracks pull request trajectories, first-comment latency, and code review rounds to help developers avoid submitting pull requests to backlogged repositories.
Currently, maintainers of cyrusagents/cyrus acknowledge new external contributions in approximately 7 days+. Out of all submitted pull requests from non-core authors in the last 180-day window, 52.8% were successfully merged into the primary branch.
cyrusagents/cyrus has a recorded first-timer success rate of 25.0%. Repositories ranked Solid typically provide actionable feedback during code reviews and actively nurture new community contributors.
The initial maintainer response time averages ~7 days+. Keeping PRs scoped to single concerns and ensuring CI checks succeed will optimize review turnaround.
The C-Rank™ index scores repositories on a 0 to 100 scale using an objective formula: external PR merge rates, initial response speed, active maintainer count, and first-time contributor retention. A score of 47.0 places cyrusagents/cyrus in the Solid tier.
The external pull request merge rate is 52.8%. GetMerged isolates non-core community contributions so external developers get an accurate benchmark of PR acceptance probability.
Yes, cyrusagents/cyrus currently has 3 active issue(s) tagged with beginner-friendly labels. You can inspect these directly from the repository issues tab.
All metrics displayed for cyrusagents/cyrus are automatically retrieved via the public GitHub API and recalculated daily. Insider pull requests submitted by repository owners or organization members are excluded from merge rate calculations to preserve objective external contributor statistics.