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.

AI agents can generate code, but still struggle to understand what they build. Reticle brings Jev-style machine-native runtime perception to web & desktop applications.

01Result

reticlehq/reticle ↗

reticlehq/reticle AI coding statistics: 77.6%

of 2,260 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

77.6% agent · top contributor 85.6%21 contributors

individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

1,753

agent commits

507

other considered commits

agent contributors

85.6%

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

1752assisted

1autonomous

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: 99.2%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	1724	76.3%
Cursor Agent	Anysphere	29	1.3%

03Evidence

Inspect the matches

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

Matched commit samples

6e91da5e on GitHubfix(bench): a cell that cannot detect must say so, not score a zeroClaude Code
20b12596 on GitHubdocs(changelog): the four user-facing changes 2.14.0 was going to ship silClaude Code
869a7919 on GitHubfix(gate): install the local registry instead of fetching it per cellClaude Code
53b6e07a on GitHubfix(init): attach to the running dev server instead of starting a second oCursor Agent
ef1419fa on GitHubfix(server): satisfy yoda lint in webgl-canvas-limit testCursor Agent
61dfc361 on GitHubfix(server): a document-key press needs no element refCursor Agent

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	2,493
Merge commits removed	−213
CI / dependency bots removed	−20
Considered	2,260

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 reticlehq/reticle

Scan another repository

Try

Month	Agent share	Considered commits
2026-06	99.2%	392
2026-07	75.1%	457
2026-08	73.3%	1122
2026-09	68.9%	289