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.

Object-storage native graph database with branching and typed ontology

01Result

ModernRelay/omnigraph ↗

ModernRelay/omnigraph AI coding statistics: 45.3%

of 960 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
45.3% agent · top contributor 28%11 contributors
org-wide

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

435
agent commits
525
other considered commits
11
agent contributors
28%
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

413assisted
22autonomous

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
2026-0465.2%112
2026-0584.8%164
2026-0670.6%238
2026-0719.4%165
2026-089.7%195
2026-094.7%86

Peak month: 84.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic39641.3%
DevinCognition222.3%
Cursor AgentAnysphere171.8%

03Evidence

Inspect the matches

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

Matched commit samples

  • 0ff0ae3b on GitHubfeat(server): readiness witness and bounded shutdown (RFC 0049) (#612)Claude Code
  • 1609ac33 on GitHubfeat(cluster): observe without the lock (RFC 0049) (#611)Claude Code
  • cbdbe17c on GitHubfix(cluster): refuse `..` segments and symbolic links in declared config pClaude Code
  • 2c578a60 on GitHub(feat) convert engine call sites to &dyn TableStorage; demote legacy TableDevin
  • b7f5276a on GitHubfix(loader): enforce composite @unique(a, b) as a true composite key (#133Devin
  • 1a4d2cee on GitHubfeat: inline query strings in CLI and HTTP server (#110)Devin
  • 8a4b6a34 on GitHubfix: make merge failpoints typed and guard all index shapesCursor Agent
  • 63b52522 on GitHubtest: reject forwarded branch-merge failpoint literalsCursor Agent
  • c9da3a93 on GitHubtest: cover forwarded failpoint names and all index shapesCursor 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 window1,142
Merge commits removed−182
CI / dependency bots removed−0
Considered960

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 ModernRelay/omnigraph

Scan another repository

Try