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.

Centaur is frontier, agentic infrastructure that you own. Centaur is like Claude Tag, but open source and on steroids.

01Result

paradigmxyz/centaur ↗

paradigmxyz/centaur AI coding statistics: 5.8%

of 964 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
5.8% agent · top contributor 30.4%14 contributors
org-wide

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

56
agent commits
908
other considered commits
14
agent contributors
30.4%
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

56assisted
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

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-052.4%210
2026-068%264
2026-078%250
2026-085.7%175
2026-090%65

Peak month: 8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic515.3%
Cursor AgentAnysphere30.3%
DevinCognition20.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • cafc4e4d on GitHubfix(api-rs): authorize githubbot for all its session key families (#1435)Claude Code
  • 98fba269 on GitHubfix(sentry): expose read-only client commands through the CLI (#1419)Claude Code
  • b28604be on GitHubfeat(githubbot): ack review-feedback turns with reactions on the review (#Claude Code
  • 5e09aaf2 on GitHubfix: do not terminalize Codex error notifications with willRetry (#1363)Cursor Agent
  • e2bdc57a on GitHubfix: honor sandbox nodeSelector, tolerations, and runtimeClassName on agenCursor Agent
  • 9fde76e3 on GitHubfix: evaluate workflow allowlist before importing modules (#1274)Cursor Agent
  • 1d5a0d56 on GitHubfeat: bind the comment author's principal on GitHub turns (#1496)Devin
  • d0ccee44 on GitHubfeat: bind the console user's principal on console thread turns (#1494)Devin

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 window998
Merge commits removed−6
CI / dependency bots removed−28
Considered964

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 →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 paradigmxyz/centaur

Scan another repository

Try