Ghost Engineering Benchmarks
Ghost delivery benchmarks are based on 563 merged pull requests in the last 30 days (3,904 all-time), with 1.7 hours median cycle time, 0.1 hours median review time, and 29 active contributors. AI-related signals appear on 3.4% of recent work. PR volume is up 15% 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 |
|---|---|---|
| Changed the dev CLI to load without tsx in a built tree | acburdine | AI |
| Avoided Unicode normalization with timing-safe equality che… | EvanHahn | — |
| Updated nx to 23.2.0 | acburdine | — |
| Changed the Koenig loader to load the bundle once | 9larsons | — |
| Changed signed member link checks to use constant-time comp… | acburdine | — |
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 2 hours, 2 minutes ago.
Updated daily from public GitHub pull requests.
See Your Team's Benchmarks