- Dataset
- 2026-09-18-v3.0
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-09-16
- Window
- February–September 15, 2026
01Result
earendil-works/pi ↗earendil-works/pi AI coding statistics: 0.3%
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. Across the whole index, 96% of agent commits are assisted.
Agent share by month
| Month | Agent share | Considered commits |
|---|---|---|
| 2026-02 | 1.5% | 330 |
| 2026-03 | 0% | 395 |
| 2026-04 | 0.2% | 423 |
| 2026-05 | 0% | 410 |
| 2026-06 | 0% | 374 |
| 2026-07 | 0.2% | 423 |
| 2026-08 | 0.4% | 822 |
| 2026-09 | 0% | 158 |
Peak month: 1.5%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 9 | 0.3% |
| Cursor Agent | Anysphere | 1 | 0% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
23002907on GitHubfeat(ai): AI Gateway transport over the Cloudflare AI binding (#7901)Claude Codeb9d360a2on GitHubfix(ai): retry transient provider errors in Google adapters (#7471)Claude Code7198e78fon GitHubfeat(agent): support custom metadata in jsonl session headers (#6417)Claude Codeb2374126on GitHubfeat(ai): generalize openai-completions thinking token budget fields (#827Cursor Agent
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 | 3,716 |
| Merge commits removed | −211 |
| CI / dependency bots removed | −170 |
| Considered | 3,335 |
Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.
05Provenance
Pinned to a source state
This observation names the repository state, release, and detector that produced it. Use these identifiers when reproducing or citing the result.
- Dataset release
- 2026-09-18-v3.0
- Scan date
- 2026-09-16
- Ruleset
- sha256:b2e8889c66f72c18a61839f0bf1a9f77b5481ba2def044dba33c797b2f2bdcae
- Canonical repository
- earendil-works/pi
- Default branch
- main
- Resolved HEAD
- 6671c604766b3670ed95f405aa7856835d0ca702 ↗
- Resolved
- 2026-09-16
- Measurement window
- February–September 15, 2026
06Peer context
Position among comparable repositories
The cohort uses the same release and measurement window, then narrows to the repository’s ecosystem and removes low-activity observations.
Midrank percentile; equal shares split the tied positions.
- Repository
- 0.3%
- Cohort median
- 5.4%
- Share rank
- 312 / 376
Percentile = (repositories below + half of 10 tied repositories) ÷ 376.
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 earendil-works/pi