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 cross-harness, self-improving memory layer for AI agents. Join our community: https://discord.com/invite/zdNChS2fBu

01Result

Asymptote-Labs/agent-beacon ↗

Asymptote-Labs/agent-beacon AI coding statistics: 71.2%

of 913 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

71.2% agent · top contributor 45.1%6 contributors

team

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

650

agent commits

263

other considered commits

agent contributors

45.1%

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

650assisted

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: 96.1%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	370	40.5%
Cursor Agent	Anysphere	282	30.9%

03Evidence

Inspect the matches

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

Matched commit samples

6e7aa3e4 on GitHubChangelog: v1.3.12Claude Code
c1c10231 on GitHubGive the user-mode inventory job its own launchd log filesClaude Code
76d69a6d on GitHubChangelog: v1.3.11Claude Code
e37cfe25 on GitHubFix JSON inspector truncating session IDs to 4-char suffixCursor Agent
92524307 on GitHubFix installed-side harness filter to normalize names before comparisonCursor Agent
ed26e842 on GitHubNormalize inherited session model through NormalizeModelNameCursor 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	1,428
Merge commits removed	−500
CI / dependency bots removed	−15
Considered	913

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 →Go AI coding statisticsCompare evidence across Go 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 Asymptote-Labs/agent-beacon

Scan another repository

Try

Month	Agent share	Considered commits
2026-05	39.5%	152
2026-06	59.7%	325
2026-07	73.7%	57
2026-08	92%	250
2026-09	96.1%	129