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.

Open-source AI Security Operations Center: alert fusion, LLM-agent triage, MITRE ATT&CK investigation, and a replayable decision ledger for every agent step. Self-hostable, runs with no API keys, MIT licensed. Ships an MCP server for Claude, Cursor and Continue.

01Result

beenuar/AiSOC ↗

beenuar/AiSOC AI coding statistics: 38.6%

of 541 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

38.6% agent · top contributor 70.3%10 contributors

team

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

209

agent commits

332

other considered commits

agent contributors

70.3%

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

204assisted

5autonomous

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: 94.6%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Cursor Agent	Anysphere	203	37.5%
Claude Code	Anthropic	6	1.1%

03Evidence

Inspect the matches

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

Matched commit samples

ca603c3d on GitHubstyle(ueba): ruff format peer_group + baseline scoring tests (#607)Cursor Agent
6123c1c8 on GitHubchore(deps): bump github/codeql-action init+autobuild+analyze to v4.37.6 (Cursor Agent
8dddf962 on GitHubfix(agents): persist investigations by resolving the 'default' tenant (#60Cursor Agent
460cc4f0 on GitHubfeat(agents,api): route LLM tasks through gateway aliases; drop default moClaude Code
dcd36682 on GitHubfix(api): reconcile detection_rules/cases schema drift on initdb installs Claude Code
6cd64cad on GitHubfeat(infra): LiteLLM gateway for task-based model routing + observability 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	753
Merge commits removed	−25
CI / dependency bots removed	−187
Considered	541

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 →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 beenuar/AiSOC

Scan another repository

Try

Month	Agent share	Considered commits
2026-05	12.1%	355
2026-06	78.3%	46
2026-07	92.2%	103
2026-08	94.6%	37