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.

01Result

0xSero/litter ↗

0xSero/litter AI coding statistics: 2.4%

of 624 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
2.4% agent · top contributor 60%3 contributors
individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

15
agent commits
609
other considered commits
3
agent contributors
60%
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

15assisted
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
2026-020%86
2026-030%90
2026-041.3%155
2026-050%148
2026-0710%10
2026-081.8%112
2026-0943.5%23

Peak month: 43.5%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic142.2%
OpenAI CodexOpenAI10.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • ac5317cc on GitHubfeat(ios): browse and resume existing on-disk sessions from home (#344)Claude Code
  • abab3e91 on GitHubfeat(models): supplement Claude catalog with CLI-resolved family aliases (Claude Code
  • 8703cedb on GitHubFloat the composer suggestion popup above the input (#342)Claude Code
  • 0c26ee73 on GitHubmobile: persist thread plan mode across relaunch (#353)OpenAI Codex

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 window667
Merge commits removed−43
CI / dependency bots removed−0
Considered624

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex 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 0xSero/litter

Scan another repository

Try