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.

The open-source agent harness - the runtime layer that turns an LLM into a working agent.

01Result

truefoundry/trueforge ↗

truefoundry/trueforge AI coding statistics: 29.5%

of 607 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

29.5% agent · top contributor 39.7%15 contributors

org-wide

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

179

agent commits

428

other considered commits

agent contributors

39.7%

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

179assisted

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: 83.9%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Cursor Agent	Anysphere	145	23.9%
Claude Code	Anthropic	36	5.9%

03Evidence

Inspect the matches

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

Matched commit samples

fd1bf7fe on GitHubfix: bump assistant-ui-runtime to 0.1.38 for completion timestamps (#754)Cursor Agent
70471bed on GitHubfix(chart): distinct Redis nameOverride vs gateway Redis (#713)Cursor Agent
8c31eae6 on GitHubfeat(agents): Support agent descriptionCursor Agent
e097f21d on GitHubdocs: replace Introduction hero image with the TrueForge overview diagram Claude Code
347a7e73 on GitHubRefresh composer, agent icon, and composer trigger styling (#578)Claude Code
d030b06e on GitHubdocs: document Daytona key snapshot permission requirement (#473)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	651
Merge commits removed	−1
CI / dependency bots removed	−43
Considered	607

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →TypeScript AI coding statisticsCompare evidence across TypeScript 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 truefoundry/trueforge

Scan another repository

Try

Month	Agent share	Considered commits
2026-07	83.9%	56
2026-08	24.4%	389
2026-09	22.8%	162