- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
Simple forum software for building great communities.
01Result
flarum/framework ↗flarum/framework AI coding statistics: 8.7%
A small group is using agents. Adoption has spread beyond one person but is not project-wide.
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 | 45.5% | 33 |
| 2026-03 | 24.6% | 114 |
| 2026-04 | 0% | 65 |
| 2026-05 | 2.1% | 47 |
| 2026-06 | 1.3% | 78 |
| 2026-07 | 4.6% | 87 |
| 2026-08 | 1.4% | 145 |
| 2026-09 | 3.8% | 26 |
Peak month: 45.5%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 49 | 8.2% |
| Cursor Agent | Anysphere | 2 | 0.3% |
| GitHub Copilot | GitHub | 1 | 0.2% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
f194386con GitHubfix: resolve translation references in implicitly-loaded fallback cataloguClaude Codedbf7f531on GitHubfix: stop the reconnect catch-up duplicating a discussion in the list (#50Claude Codeca6ca2cbon GitHub[2.x] fix(realtime): honour user.viewLastSeenAt in the typing indicator (#Claude Code3ec84b2don GitHubfix(forum): show pop-in animation on first post when loading discussion (#Cursor Agent7cdad539on GitHubfix(forum): prevent scroll jump when loading discussion to specific post (Cursor Agent4d5f866eon GitHubfeat: add support for customizable user avatar drivers (#4130)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 | 626 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −31 |
| Considered | 595 |
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 flarum/framework