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.

Model router for agentic systems. Routes every prompt to the right model in <50ms. Cut costs 40-70% with just an endpoint change.

01Result

weave-os/router ↗

weave-os/router AI coding statistics: 52.5%

of 1,079 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
52.5% agent · top contributor 51.7%9 contributors
team

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

567
agent commits
512
other considered commits
9
agent contributors
51.7%
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

390assisted
177autonomous

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
2026-040%1
2026-0545.2%239
2026-0679.7%236
2026-0746.2%221
2026-0840.7%216
2026-0948.8%166

Peak month: 79.7%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic32630.2%
DevinCognition17816.5%
Cursor AgentAnysphere666.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • a7ca36bf on GitHubfeat(router): give the beta HMM strategy its own declarative roster (#1153Claude Code
  • 966bc9f4 on GitHubfeat(catalog): add grok-4.6 (xAI flagship, 2026-08-12) (#904)Claude Code
  • 85da27b3 on GitHubfix(anthropic): stop claiming the OAuth beta on deployment-key auth (#856)Claude Code
  • 5c0545b9 on GitHubproxy/translate: flag-gated cc_workspace_system_append for cross-vendor ClDevin
  • d2546070 on GitHubLog block finality on a committed stream cut (#1331)Devin
  • d332c5af on GitHubClassifier turns: pass through on Claude subscription, otherwise score; flDevin
  • a064e631 on GitHubfix(auth): reject RotateAPIKey when SoftDelete affects 0 rows (#822)Cursor Agent
  • 0ec3b0cf on GitHubfix(rl): send X-Weave-Band-* headers for Modal band serve (#723)Cursor Agent
  • 3033cf14 on GitHubfeat(rl): Modal proxy auth headers for policy sidecar (#722)Cursor 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 window1,080
Merge commits removed−0
CI / dependency bots removed−1
Considered1,079

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 →Devin commitsBrowse repositories with detected Devin 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 weave-os/router

Scan another repository

Try