- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
Extended Ralph loop for autonomous AI-driven plan execution
01Result
umputun/ralphex ↗umputun/ralphex AI coding statistics: 5%
Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.
02Drivers
What shapes this result
Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.
Assisted or autonomous
Assisted — a developer’s identity authored the commit and the agent added itself as co-author. Autonomous — a bot identity authored the commit without a human identity attached.
Agent share by month
| Month | Agent share | Considered commits |
|---|---|---|
| 2026-02 | 3.3% | 150 |
| 2026-03 | 8.3% | 96 |
| 2026-04 | 2.8% | 36 |
| 2026-05 | 2.4% | 41 |
| 2026-06 | 0% | 13 |
| 2026-07 | 8.3% | 12 |
| 2026-08 | 0% | 23 |
| 2026-09 | 25% | 12 |
Peak month: 25%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 18 | 4.7% |
| GitHub Copilot | GitHub | 1 | 0.3% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
604f78c5on GitHubfix: strip all Claude Code session env vars from child processes (#430)Claude Code1d176549on GitHubfix: match claude limit patterns by diagnostic provenanceClaude Code6f0ebeeaon GitHubfix: return repo-relative paths with forward slashes so the plan file exclClaude Code02715b00on GitHubAdd GitHub Copilot CLI support (#275)GitHub Copilot
04Method
What entered the denominator
The result begins with commit history, removes merges and routine automation, and reports literal agent signatures as a lower bound.
Exclusion ledger
| Commits in window | 415 |
| Merge commits removed | −6 |
| CI / dependency bots removed | −26 |
| Considered | 383 |
Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.
Continue exploring
Related coding-agent evidence
Run the same detector locally.
Deterministic signature matching; no code-style inference. Squash merges can remove trailers, so this result remains a measured floor.
npx qmmit-cli umputun/ralphex