- Dataset
- 2026-09-18-v3.0
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-09-16
- Window
- February–September 15, 2026
01Result
ComposioHQ/composio ↗ComposioHQ/composio AI coding statistics: 46.7%
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 | 70.6% | 504 |
| 2026-03 | 64.4% | 427 |
| 2026-04 | 49.6% | 236 |
| 2026-05 | 54.6% | 229 |
| 2026-06 | 31.7% | 123 |
| 2026-07 | 24.4% | 201 |
| 2026-08 | 15% | 347 |
| 2026-09 | 9.4% | 127 |
Peak month: 70.6%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 996 | 45.4% |
| Cursor Agent | Anysphere | 14 | 0.6% |
| Devin | Cognition | 14 | 0.6% |
| GitHub Copilot | GitHub | 1 | 0% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
876c8876on GitHubfix(core): normalize a missing toolkit auth field group instead of throwinClaude Codea5f52aceon GitHubperf(cli): list connected accounts once per executeClaude Code0a1464d5on GitHubperf(cli): move the compiler and tokenizer out of the executableClaude Codeaacbc97aon GitHubdocs(claude-code-plugin): add page for Claude Code plugin install pathCursor Agent4fda636aon GitHubchore(cli): migrate binary release tags and docs (#2719)Cursor Agent2648fcaaon GitHubfeat(cli): add logs commands for triggers and tools (#2742)Cursor Agentda704439on GitHubdocs(proxy-execute): note cross-domain requests are not allowedDevinf17f5b6bon GitHubdocs(proxy-execute): address review feedbackDevin2518d5c2on GitHubchore(gitleaks): ignore placeholder curl example in proxy-execute docsDevina6bd593eon GitHubUpdate docs/content/docs/managing-multiple-connected-accounts.mdxGitHub 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 | 3,100 |
| Merge commits removed | −754 |
| CI / dependency bots removed | −152 |
| Considered | 2,194 |
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
- ComposioHQ/composio
- Default branch
- next
- Resolved HEAD
- 7a63e5acd74ae2ed35bb8b1710494b27c6782d61 ↗
- 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
- 46.7%
- Cohort median
- 5.4%
- Share rank
- 24 / 376
Percentile = (repositories below + half of 1 tied repository) ÷ 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 ComposioHQ/composio