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.

🚀 The open-source, multi-tenant platform for self-building knowledge graphs and simulation

01Result

hashintel/hash ↗

hashintel/hash AI coding statistics: 25.3%

of 847 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
25.3% agent · top contributor 42.5%11 contributors
org-wide

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

214
agent commits
633
other considered commits
11
agent contributors
42.5%
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

99assisted
115autonomous

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
2026-026.5%92
2026-0323.7%59
2026-0420%40
2026-056.8%74
2026-0615.7%83
2026-0744.7%123
2026-0830.9%178
2026-0929.3%198

Peak month: 44.7%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic15818.7%
Cursor AgentAnysphere455.3%
GitHub CopilotGitHub212.5%

03Evidence

Inspect the matches

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

Matched commit samples

  • 9050765c on GitHubFE-1723: Cap the size of Petrinaut's Open submenu and elide long net titleClaude Code
  • a898a138 on GitHubFE-1721: Sort the open-document list by `lastUpdated`, most recent first (Claude Code
  • 4b1e2c23 on GitHubSRE-1057: Run the housekeeping workflow once a day at 03:00 UTC (#9735)Claude Code
  • 8b22b6f2 on GitHubFE-1725: Remember Petrinaut Voice disclosure for Live (#9748)Cursor Agent
  • 36d777cf on GitHubFE-1722: Improve Brunch Voice controls (#9747)Cursor Agent
  • 297275ba on GitHubFE-1664: Land remaining voice stack changes (#9745)Cursor Agent
  • e4bd5c41 on GitHubBE-743: Make the semantic-search candidate pool and ef_search configurableGitHub Copilot
  • b3229779 on GitHubFE-1418: Build @apps/petrinaut-docs on Vercel (#9232)GitHub Copilot
  • 2f13c996 on GitHubSRE-884: Remove the legacy health endpoints (#9133)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 window999
Merge commits removed−0
CI / dependency bots removed−152
Considered847

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 hashintel/hash

Scan another repository

Try