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.

1 place to call all your agents - OpenCode, Hermes, Claude Managed Agents, Cursor Agents API, DeepAgents.

01Result

LiteLLM-Labs/litellm-agent-control-plane ↗

LiteLLM-Labs/litellm-agent-control-plane AI coding statistics: 30.6%

of 1,171 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

30.6% agent · top contributor 86.3%6 contributors

individual

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

358

agent commits

813

other considered commits

agent contributors

86.3%

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

358assisted

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: 31.8%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	336	28.7%
OpenAI Codex	OpenAI	18	1.5%
Cursor Agent	Anysphere	4	0.3%

03Evidence

Inspect the matches

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

Matched commit samples

18f17614 on GitHubdocs(templates): add AGENTS.md pointing to the create-harness skill (#423)Claude Code
fdcfed8f on GitHubfeat(runtime): add Elastic Agent Builder runtime provider (#421)Claude Code
756946a8 on GitHubfeat: add open-harness-sdk and root tsconfigClaude Code
f09bcc48 on GitHubFix inbox approval item selection (#432)OpenAI Codex
c6308da2 on GitHubServe inbox RSC payload at client route (#431)OpenAI Codex
0688d561 on GitHubPrevent stale inbox shell caching (#430)OpenAI Codex
089105b7 on GitHubfix(issue-reporter): use session-scoped endpoint, drop agent_id requiremenCursor Agent
f70a70e0 on GitHubfeat(e2b): pre-bake proxy stack and add sandbox diagnosticsCursor Agent
2a442510 on GitHubdebug(inline-harness): log when inline URL env is missingCursor 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	1,359
Merge commits removed	−188
CI / dependency bots removed	−0
Considered	1,171

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →Rust AI coding statisticsCompare evidence across Rust 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 LiteLLM-Labs/litellm-agent-control-plane

Scan another repository

Try

Month	Agent share	Considered commits
2026-05	31.8%	1059
2026-06	18.8%	112