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.

A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.

01Result

zilliztech/memsearch ↗

zilliztech/memsearch AI coding statistics: 34%

of 400 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

34% agent · top contributor 95.6%3 contributors

individual

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

136

agent commits

264

other considered commits

agent contributors

95.6%

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

133assisted

3autonomous

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: 93.7%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	133	33.3%
GitHub Copilot	GitHub	3	0.8%

03Evidence

Inspect the matches

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

Matched commit samples

97a7b336 on GitHubfix: force encoding_format=float for OpenAI-compatible endpoints (#302)Claude Code
f3f190d0 on GitHubstyle: fix ruff format violations in 6 files (#285)Claude Code
cd67906f on GitHubchore: bump ccplugin version to 0.2.7Claude Code
215fc74d on GitHubSupport env:VAR_NAME format for compact base_url and api_key in _compact_oGitHub Copilot
05fa69f6 on GitHubAdd independent OpenAI-compatible API endpoint config for compact moduleGitHub Copilot
b6f5945c on GitHubInitial planGitHub Copilot

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	463
Merge commits removed	−63
CI / dependency bots removed	−0
Considered	400

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 →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 zilliztech/memsearch

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	93.7%	126
2026-03	16.8%	95
2026-04	3%	66
2026-05	0%	17
2026-06	0%	29
2026-07	0%	30
2026-08	0%	28
2026-09	0%	9