Runs coding agents as a graph: one agent implements, independent agents review, failures go to repair, and nothing ships until the checks pass. Works with Codex, Claude Code and Copilot. Bring your own topology.
C-Rank Grade: A (Welcoming) - 69/100
External PR Merge Rate: 81%
Response Time: 4d
First Timer Success: 50%
the-open-engine/zeroshot has a recorded first-timer success rate of 50.0%. Repositories ranked A typically provide actionable feedback during code reviews and actively nurture new community contributors.
Maintainers in the-open-engine/zeroshot respond to incoming external pull requests in approximately 107.3 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 69.0 places the-open-engine/zeroshot in the A tier.
The external contributor pull request merge rate for the-open-engine/zeroshot is 81.5%, based on public PR activity from non-core contributors.
the-open-engine/zeroshot currently has 8 active issue(s) tagged with beginner-friendly labels like "good first issue", "beginner", or "up-for-grabs".
Active JavaScript repository in the-open-engine/zeroshot with ongoing community development and issue triage.
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/the-open-engine/zeroshot?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 21:00 UTC (21:00 UTC in your timezone). Recommended submission window is Monday - Wednesday from 19:00 to 23:00 UTC (19:00 - 23:00 UTC local).
Maintainer Strategy: Maintainer Sweet Spot: PRs under 150 lines merge in ~70 hours (96% approval). Large PRs (>500 lines) take ~515 hours (37% approval). Keep your diff compact for rapid review.
Description Each agent gets its own TMPDIR like ~/.local/state/zeroshot/runs/<uuid>/runtime/execution-18/tmp, already about 100 characters. Go's t.TempDir() appends the test name plus a random number, and a socket name on top of that lands around 170 characters. Linux limits a Unix socket path to 108 bytes, so bind() fails with invalid argument and every test that creates a socket in a temp dir fails for the directory name alone. Expected A short per-run TMPDIR, for example under /tmp/zs-<short-id>/, or a documented override, so socket-based tests behave as they do outside Zeroshot. Reported in the community Discord (#feedback); filed here so it can be claimed. Reporter: Torstein.
Description A reviewer wanted to know whether failing tests also failed on the base revision. It stashed the working tree and checked out the base revision over it inside the worktree, which discarded the worker's changes. The following review-repair node then started from a worktree missing most of the previous work. Expected Reviewer nodes should not be able to destroy the candidate change. Either run them against a read-only snapshot, give them a separate checkout for base comparisons, or block destructive Git commands in review roles. Reported in the community Discord (#feedback); filed here so it can be claimed. Reporter: Torstein.
Problem Supported harnesses are Codex, Claude Code and Copilot. Users on OpenCode or pi cannot run Zeroshot with the agent they already use. Proposal Add harness adapters for OpenCode and pi. Earlier OpenCode support existed in the Node-era product (#390, #530) and does not carry over. Reported in the community Discord (#feedback); filed here so it can be claimed. Reporter: Andrey, who offered to contribute.
Problem Running on a VPS under Tailscale, the latest release explicitly forbids binding to anything but the loopback address, so the UI and API can only be reached through an extra tunnel. Proposal Allow an explicit opt-in bind address, for example a Tailscale interface, with the existing authentication still required. Reported in the community Discord (#feedback); filed here so it can be claimed. Reporter: Andrey.
Description About four hours into a long run, five verifiers started in parallel and all got 400 Grammar compilation rate limit exceeded. You can try again later. from the Copilot API. Each retried immediately (attempt 2), hit the same limit within seconds, and the run ended review_failed. The same nodes had passed two rounds earlier. Probable trigger: every session.send uses responseFormat: json_schema, strict: true, so each session costs the backend a grammar compilation. Expected Rate-limit responses are retried with backoff, ideally staggered across parallel nodes, rather than counted as a review failure. Reported in the community Discord (#feedback); filed here so it can be claimed. Reporter: Torstein.
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 the-open-engine/zeroshot, 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 the-open-engine/zeroshot acknowledge new external contributions in approximately 4 days+. Out of all submitted pull requests from non-core authors in the last 180-day window, 81.5% were successfully merged into the primary branch.
the-open-engine/zeroshot has a recorded first-timer success rate of 50.0%. Repositories ranked Welcoming typically provide actionable feedback during code reviews and actively nurture new community contributors.
The initial maintainer response time averages ~4 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 69.0 places the-open-engine/zeroshot in the Welcoming tier.
The external pull request merge rate is 81.5%. GetMerged isolates non-core community contributions so external developers get an accurate benchmark of PR acceptance probability.
Yes, the-open-engine/zeroshot currently has 8 active issue(s) tagged with beginner-friendly labels. You can inspect these directly from the repository issues tab.
All metrics displayed for the-open-engine/zeroshot 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.