Dataset: 2026-10-27-catalog-ai-v2
Ruleset: b2e8889c66f7
Scanned: 2026-10-27
Window: February–September 15, 2026

Catalog tracking observation. This repository is measured with the same fixed window and ruleset, but it is not part of the published benchmark or its aggregate claims.

🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai

01Result

kayba-ai/agentic-context-engine ↗

kayba-ai/agentic-context-engine AI coding statistics: 39.2%

of 459 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

39.2% agent · top contributor 43.3%7 contributors

team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

180

agent commits

279

other considered commits

agent contributors

43.3%

largest contributor

02Drivers

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

180assisted

0autonomous

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

Peak month: 54%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	180	39.2%

03Evidence

Inspect the matches

Public commit samples let you inspect the signatures behind the aggregate result.

Matched commit samples

f2c912a9 on GitHubfeat(rr): add usage metering hook and pre-built model support (0.10.0) (#1Claude Code
0d6d014e on GitHubdocs: replace pip install with uv add across all docsClaude Code
d0d09cc4 on GitHubchore: bump version to 0.9.0 for PydanticAI migrationClaude Code

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	532
Merge commits removed	−73
CI / dependency bots removed	−0
Considered	459

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →Python AI coding statisticsCompare evidence across Python repositories →GitHub AI commit analyzerInspect another repository with the same evidence model →

Reproduce this observation

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 kayba-ai/agentic-context-engine

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	54%	187
2026-03	45.1%	173
2026-04	1.4%	70
2026-05	0%	21
2026-06	0%	3
2026-08	0%	2
2026-09	0%	3