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.

A desktop app for isolated, parallel agentic development

coder/xum ↗

coder/xum AI coding statistics: 0.8%

of 1,755 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
0.8% agent · top contributor 78.6%4 contributors
team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

14
agent commits
1,741
other considered commits
4
agent contributors
78.6%
largest contributor

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

14assisted
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%505
2026-032.5%315
2026-040%88
2026-051.1%182
2026-060.5%198
2026-071.1%87
2026-081%203
2026-090%177

Peak month: 2.5%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
OpenAI CodexOpenAI80.5%
Claude CodeAnthropic60.3%

Inspect the matches

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

Matched commit samples

  • b243ff98 on GitHub🤖 fix: sanitize docker UID/GID before docker exec chown (#2980)OpenAI Codex
  • 557637e4 on GitHub🤖 fix: prevent shell injection in devcontainer native terminal launch (#2OpenAI Codex
  • ff743d1d on GitHub🤖 fix: harden git check-ignore script quoting (#2940)OpenAI Codex
  • c3aa2a63 on GitHubterminal-bench: stop uploading benchmark artifacts (#4002)Claude Code
  • 93244e0c on GitHub🤖 fix: restore ${os} token in release artifact names (#3927)Claude Code
  • c569b229 on GitHub🤖 feat: redesign workspace chrome (footer info bar, title header, creatioClaude Code

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 window1,832
Merge commits removed−0
CI / dependency bots removed−77
Considered1,755

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

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 coder/xum

Scan another repository