Pulse
2026-09-18-v3.0
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.

Laminar - open-source observability platform purpose-built for AI agents. YC S24.

01Result

lmnr-ai/lmnr ↗

lmnr-ai/lmnr AI coding statistics: 47.5%

of 788 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
47.5% agent · top contributor 68.7%10 contributors
team

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

374
agent commits
414
other considered commits
10
agent contributors
68.7%
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

117assisted
257autonomous

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

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-0214.9%94
2026-0346.2%119
2026-0437.6%157
2026-0560.5%76
2026-0667.3%98
2026-0761.2%121
2026-0856.5%69
2026-0938.9%54

Peak month: 67.3%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic36846.7%
Cursor AgentAnysphere192.4%
GitHub CopilotGitHub10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 799128e3 on GitHubLAM-2248: shared per-scope cache for LLM feature routes, 30-day default enClaude Code
  • fb0acf6d on GitHubLAM-2248: llm_feature_routes replaces per-feature LLM provider env vars (OClaude Code
  • 540a5c75 on GitHubLAM-2243: port signal/cluster ClickHouse schema to OSS and rewrite trace-vClaude Code
  • 615dc130 on GitHubfeat: support Azure as an LLM provider (LAM-2147) (#2231)Cursor Agent
  • da800580 on GitHubLAM-2111: log ingestion rate-limit rejections (#2198)Cursor Agent
  • ccae5f1e on GitHubLAM-2126: separate signal trigger, filters, and mode in the API (#2217)Cursor Agent
  • 5a7136f3 on GitHubci: publish native multi-arch container images (#2216)GitHub 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 window844
Merge commits removed−45
CI / dependency bots removed−11
Considered788

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent 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 lmnr-ai/lmnr

Scan another repository

Try