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.

Open-source observability for AI agents. Find where your agents fail, dispatch your coding agent to fix it, and verify the fix against real traces.

01Result

latitude-dev/latitude-llm ↗

latitude-dev/latitude-llm AI coding statistics: 38.1%

of 1,993 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
38.1% agent · top contributor 45.5%20 contributors
org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

759
agent commits
1,234
other considered commits
20
agent contributors
45.5%
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

704assisted
55autonomous

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
2026-0219.5%236
2026-0329.7%145
2026-0430.1%362
2026-0536%322
2026-0642.5%393
2026-0745.4%350
2026-0867.7%93
2026-0960.9%92

Peak month: 67.7%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic54427.3%
Cursor AgentAnysphere23711.9%
GitHub CopilotGitHub30.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • fe3d1fbd on GitHubdocs: product catch-up — Cost, migration guide, signals promotion and feedClaude Code
  • 08a6a112 on GitHubfeat(telemetry): rewrite the OpenClaw plugin for 2026.8+ and ship 0.1.0 (#Claude Code
  • 513d77aa on GitHubfeat(billing): usage breakdown by product area and project in the sidebar Claude Code
  • d482e27f on GitHubchore(biome): reduce cognitive complexity in apps/ingest (#4585)Cursor Agent
  • 6c7f7a9e on GitHubchore(biome): reduce cognitive complexity in conversation-intelligence (#4Cursor Agent
  • 24ff7b64 on GitHubchore(biome): reduce cognitive complexity in operations handlers (#4582)Cursor Agent
  • 271fa400 on GitHubFix docu integration CC - Latitude v2 (#2798)GitHub Copilot
  • c3bc71ec on GitHubAdd scalable live ingestion seed tool (#2752)GitHub Copilot
  • 243c6c0c on GitHubFix magic link login reliability and failure handling (#2503)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 window2,320
Merge commits removed−1
CI / dependency bots removed−326
Considered1,993

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 latitude-dev/latitude-llm

Scan another repository

Try