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.

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.

01Result

omnigent-ai/omnigent ↗

omnigent-ai/omnigent AI coding statistics: 3.9%

of 3,504 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
3.9% agent · top contributor 13%68 contributors
org-wide

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

138
agent commits
3,366
other considered commits
68
agent contributors
13%
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

134assisted
4autonomous

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
2026-064.6%981
2026-073.2%1108
2026-082.7%930
2026-096.6%485

Peak month: 6.6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic1253.6%
Cursor AgentAnysphere60.2%
OpenAI CodexOpenAI40.1%
GitHub CopilotGitHub40.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • b71c37b6 on GitHubfix(native): persist Plan state across Server restarts (#6629)Claude Code
  • 4b90a6e8 on GitHubfeat(web): add default Workspace tab preference (#4844)Claude Code
  • 58a87125 on GitHubfix(web): name Claude sub-agents by their task (#4061)Claude Code
  • aae2259d on GitHubfix(claude-native): pass provider model overrides to Claude (#6385)Cursor Agent
  • 393d6b50 on GitHubfix(electron): Linux .deb missing desktop launcher icon (#3396)Cursor Agent
  • f4e93c2b on GitHubfix(server): 409 when delete_branch cannot reach an offline runner (#6190)Cursor Agent
  • 93fb7e7a on GitHubfeat(db): add CockroachDB backend support (#6360)OpenAI Codex
  • 0e2bef9a on GitHubfeat(web): add Solarized color theme (#6906)OpenAI Codex
  • c46122dc on GitHubfix(kimi): steer queued messages with ctrl-s (#6439)OpenAI Codex
  • a71df6c1 on GitHubfix(host): generate host_id when config.yaml provides only a host name (#4GitHub Copilot
  • 50e6bd85 on GitHubtest(runner-init): guard fork-history directives survive the reconnect envGitHub Copilot
  • 24509aa5 on GitHubfix(sandbox): bind target binary into bwrap namespace; un-quarantine 4 claGitHub 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 window3,746
Merge commits removed−25
CI / dependency bots removed−217
Considered3,504

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →Python AI coding statisticsCompare evidence across Python 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 omnigent-ai/omnigent

Scan another repository

Try