Pulse
2026-09-18-v3.0
Dataset
2026-09-18-v3.0
Ruleset
b2e8889c66f7
Scanned
2026-09-16
Window
February–September 15, 2026
Local to this browser

01Result

NousResearch/hermes-agent ↗

NousResearch/hermes-agent AI coding statistics: 2.6%

of 32,137 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
2.6% agent · top contributor 6%347 contributors
org-wide

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

828
agent commits
31,309
other considered commits
347
agent contributors
6%
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

827assisted
1autonomous

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. Across the whole index, 96% of agent commits are assisted.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-010%1
2026-023.3%426
2026-030.9%1917
2026-043.7%3691
2026-053.7%3148
2026-062.7%3350
2026-073.5%5511
2026-082.8%6516
2026-091.1%7577

Peak month: 3.7%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic6992.2%
Cursor AgentAnysphere1000.3%
GitHub CopilotGitHub270.1%
OpenAI CodexOpenAI40%
Other / generic agentVarious10%

03Evidence

Inspect the matches

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

Matched commit samples

  • 1034215a on GitHubdocs(free-tier): drop the rehearsal page and its referencesClaude Code
  • 2a94ca80 on GitHubfix(free-tier): review round 2 — route-gate the allowance verdict, keep poClaude Code
  • a241f42f on GitHubcopy(free-tier): "it's free" without "keeps the free model" — signed-in frClaude Code
  • 3ccad12c on GitHubfix(desktop): preserve reading intent across history and pane changesCursor Agent
  • dab6fe29 on GitHubfix(update): drop untrusted fleet fallback versionCursor Agent
  • 8b3059fc on GitHubfix(cron): keep self-removed runs alive across post-removal heartbeatsCursor Agent
  • 0b50c8e4 on GitHubci: wrap uv python install in retry action on OS test laneGitHub Copilot
  • 141d5db9 on GitHubfix(cron): scope in_channel thread_id clear to the live-send/seed gateGitHub Copilot
  • 5f2fdf66 on GitHubfeat: per-model compression threshold overrides (v2, rebased on main)GitHub Copilot
  • b595fcd5 on GitHubfix(desktop): keep the Linux HUD clickable and recoverableOpenAI Codex
  • cfb55de5 on GitHubUpdate Stripe Projects skill docs (#48673)OpenAI Codex
  • 17588521 on GitHubfix(docs): align fallback provider config examplesOpenAI Codex
  • 7ebebfbb on GitHubHarden Skills Guard multi-word prompt patterns (#26852)Other / generic 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 window35,373
Merge commits removed−2,880
CI / dependency bots removed−356
Considered32,137

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

05Provenance

Pinned to a source state

This observation names the repository state, release, and detector that produced it. Use these identifiers when reproducing or citing the result.

Dataset release
2026-09-18-v3.0
Scan date
2026-09-16
Ruleset
sha256:b2e8889c66f72c18a61839f0bf1a9f77b5481ba2def044dba33c797b2f2bdcae
Canonical repository
NousResearch/hermes-agent
Default branch
main
Resolved HEAD
784d5c3f9c2cb77698d8a9d2e72b1d106a38ea88 ↗
Resolved
2026-09-16
Measurement window
February–September 15, 2026
Download observation JSONDeterministic export · same values as this page

06Peer context

Position among comparable repositories

The cohort uses the same release and measurement window, then narrows to the repository’s ecosystem and removes low-activity observations.

CohortPython · 247 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 145 of 392 ecosystem repositories excluded
Agent-commit share position32nd percentile

Midrank percentile; equal shares split the tied positions.

Repository
2.6%
Cohort median
6.3%
Share rank
167 / 247
0th50th100th

Percentile = (repositories below + half of 2 tied repositories) ÷ 247.

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 →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 NousResearch/hermes-agent

Scan another repository

Try