Ghost Engineering Benchmarks
Ghost delivery benchmarks are based on 906 merged pull requests in the last 30 days (5,040 all-time), with 1.2 hours median cycle time, 0.2 hours median review time, and 32 active contributors. AI-related signals appear on 13.7% of recent work. PR volume is up 95% compared to the prior period.
Repo vs Ghost Average
Delivery Trend and AI Signals
PR Backlog (Humans)
Excludes AI agents and automation accounts.
PR Backlog (AI Agents)
AI coding agents only.
Cycle Time by AI-Related Signals
PR Breakdown
Top AI Tools
PR Type Breakdown
Recent Pull Requests
View PR Explorer| Title | Author | AI |
|---|---|---|
| Updated member attribution to boot-owned initialization | ErisDS | — |
| Moved Integrations composition into boot | ErisDS | — |
| Improved module-cache cleanup in service fixtures | ErisDS | — |
| Improved service migration review guardrails | ErisDS | — |
| Added exhaustive automation status check | cmraible | — |
Methodology
Metrics are computed from merged pull request data synced daily from GitHub. AI-related metrics are directional signals inferred from pull request activity patterns and heuristics. Summary metrics use a 30-day rolling window; trends use a 90-day window. Last updated 15 hours, 7 minutes ago.
Updated daily from public GitHub pull requests.
See Your Team's Benchmarks