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

odysseus-dev/odysseus ↗

odysseus-dev/odysseus AI coding statistics: 9%

of 2,002 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
9% agent · top contributor 16%75 contributors
org-wide

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

181
agent commits
1,821
other considered commits
75
agent contributors
16%
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

181assisted
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. Across the whole index, 96% of agent commits are assisted.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-050%1
2026-069.3%1769
2026-079.8%122
2026-083%100
2026-0910%10

Peak month: 10%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic1748.7%
Cursor AgentAnysphere70.3%

03Evidence

Inspect the matches

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

Matched commit samples

  • affaee1e on GitHubfix(discovery): cache a successful but empty Tailscale lookup (#6228)Claude Code
  • adfe3ab3 on GitHubfix(llm): alias tool names that collide with gpt-oss built-ins (#5878)Claude Code
  • bea48c74 on GitHubfix(sidebar): keep minimized icon rail in sync with per-tab visibility (#5Claude Code
  • 08e1d05f on GitHubfix(hwfit): repair remote Windows hardware scan over SSH (#4674)Cursor Agent
  • 08035f35 on GitHubfix(kimi): resolve Kimi Code API 403 errors and User-Agent restrictions (#Cursor Agent
  • adbd626c on GitHubfeat(chat): recall last user message on empty composer ArrowUp (#1175)Cursor 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 window2,090
Merge commits removed−80
CI / dependency bots removed−8
Considered2,002

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
odysseus-dev/odysseus
Default branch
dev
Resolved HEAD
3b6c169162330cd35c4ce6d14949ef15fd3208a2 ↗
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 position58th percentile

Midrank percentile; equal shares split the tied positions.

Repository
9%
Cohort median
6.3%
Share rank
105 / 247
0th50th100th

Percentile = (repositories below + half of 1 tied repository) ÷ 247.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →Cursor Agent commitsBrowse repositories with detected Cursor Agent 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 odysseus-dev/odysseus

Scan another repository

Try