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.

Private web search for AI assistants via SearXNG — supports Claude, Cursor, and any MCP client

01Result

ihor-sokoliuk/mcp-searxng ↗

ihor-sokoliuk/mcp-searxng AI coding statistics: 28.1%

of 437 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

28.1% agent · top contributor 85.4%9 contributors

individual

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

123

agent commits

314

other considered commits

agent contributors

85.4%

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

116assisted

7autonomous

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: 62.5%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	111	25.4%
OpenAI Codex	OpenAI	37	8.5%
GitHub Copilot	GitHub	12	2.7%

03Evidence

Inspect the matches

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

Matched commit samples

4ada34fd on GitHubfix(search): harden search metadata rendering against untrusted responsesClaude Code
7f0c21f0 on GitHubfix: fail closed on partial engine capability discoveryClaude Code
0f0df193 on GitHubfix: validate time range engine supportClaude Code
e7a389ec on GitHubfeat(search): add in-memory search result cache (FEAT-008)OpenAI Codex
e9542547 on GitHubdocs(security): reword absolute phrasing flagged by Codacy prose ruleOpenAI Codex
01cd419c on GitHubtest(resources): assert redacted searxngUrl host via URL parsing, not subsOpenAI Codex
2fc04877 on GitHubPotential fix for pull request findingGitHub Copilot
b38362a6 on GitHubchore(deps-dev): keep eslint at 10.7.0 for Node >=20 compatibilityGitHub Copilot
d2ea9ef5 on GitHubPotential fix for pull request findingGitHub 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	475
Merge commits removed	−0
CI / dependency bots removed	−38
Considered	437

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex 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 ihor-sokoliuk/mcp-searxng

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	62.5%	8
2026-03	33.3%	12
2026-04	13.9%	36
2026-05	0%	7
2026-06	41.4%	145
2026-07	30.4%	148
2026-08	6.3%	48
2026-09	3%	33