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.

Bonsai Demo

01Result

PrismML-Eng/Bonsai-demo ↗

PrismML-Eng/Bonsai-demo AI coding statistics: 33.3%

of 123 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

33.3% agent · top contributor 39%11 contributors

org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

agent commits

other considered commits

agent contributors

39%

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

25assisted

16autonomous

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

Which agents

Agent	Vendor	Commits	Share
GitHub Copilot	GitHub	33	26.8%
Claude Code	Anthropic	8	6.5%

03Evidence

Inspect the matches

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

Matched commit samples

714e5a0d on GitHubcommunity-benchmarks: L40S Bonsai-27B (ternary + binary, with/without DSpaGitHub Copilot
3921454d on GitHubsetup.ps1: refresh Windows binaries on release-tag change (#78)GitHub Copilot
751b86af on GitHubModification to run_llama.ps1 (#74)GitHub Copilot
1d8f2f68 on GitHubfix: honor BONSAI_KV4 on Windows and BONSAI_SPEC_NMAX in the shell server Claude Code
8ccc586d on GitHubdocs: Q2_0 CUDA merged upstream; dspark drafter still fork-only (#141)Claude Code
5f0ab2c9 on GitHubcommunity-benchmarks: RTX A5000 (CUDA) entry for Ternary-Bonsai-27B (#97)Claude 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	130
Merge commits removed	−7
CI / dependency bots removed	−0
Considered	123

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 →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →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 PrismML-Eng/Bonsai-demo

Scan another repository

Try

Month	Agent share	Considered commits
2026-03	33.3%	6
2026-04	49.2%	65
2026-05	100%	2
2026-07	9.1%	33
2026-08	14.3%	14
2026-09	0%	3