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 gateway / AI control plane / AI proxy written in Go. Unified OpenAI-compatible and Anthropic-compatible API for OpenAI, Anthropic, Gemini, Groq, xAI, Ollama, vLLM and more. A LiteLLM alternative with observability, guardrails, streaming, cost tracking, intelligent routing, sticky sessions, failover, real-time logs and usage tracking. Prod ready.

01Result

ENTERPILOT/GoModel ↗

ENTERPILOT/GoModel AI coding statistics: 31.1%

of 856 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

31.1% agent · top contributor 90.6%8 contributors

individual

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

266

agent commits

590

other considered commits

agent contributors

90.6%

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

262assisted

4autonomous

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: 79.6%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	262	30.6%
GitHub Copilot	GitHub	4	0.5%

03Evidence

Inspect the matches

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

Matched commit samples

63cc886d on GitHubfix(zai): forward reasoning effort as reasoning_effort (#999)Claude Code
db499655 on GitHubfix(dashboard): declutter the workflow card and editor (#919)Claude Code
587b1de9 on GitHubfeat(audit): record every prompt guardrail edit as its own revision (#917)Claude Code
775bbaab on GitHubchore(deps): bump the gomod group with 8 updates (#604)GitHub Copilot
5db0499b on GitHubchore(deps): bump github.com/aws/aws-sdk-go-v2/config (#366)GitHub Copilot
28107f94 on GitHubUpdate internal/server/handlers.goGitHub 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	961
Merge commits removed	−17
CI / dependency bots removed	−88
Considered	856

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 →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 ENTERPILOT/GoModel

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	18.3%	142
2026-03	17.6%	102
2026-04	7.7%	91
2026-05	47.7%	44
2026-06	79.6%	49
2026-07	70.3%	145
2026-08	18.6%	145
2026-09	18.8%	138