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.

Zig code intelligence server and MCP toolset for AI agents. Fast tree, outline, symbol, search, read, edit, deps, snapshot, and remote GitHub repo queries.

01Result

justrach/codedb ↗

justrach/codedb AI coding statistics: 64.9%

of 886 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
64.9% agent · top contributor 68.9%7 contributors
team

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

575
agent commits
311
other considered commits
7
agent contributors
68.9%
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

575assisted
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
2026-0335.5%62
2026-0471.7%212
2026-0574.2%221
2026-0695.6%182
2026-0745.9%74
2026-0824.2%120
2026-090%15

Peak month: 95.6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic54761.7%
DevinCognition202.3%
Cursor AgentAnysphere91%

03Evidence

Inspect the matches

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

Matched commit samples

  • 03d72fe6 on GitHubfix(mcp): advertise readOnlyHint on every read-only toolClaude Code
  • 1cc30d94 on GitHubfix(#682): callers stops counting trailing-comment mentions as call sitesClaude Code
  • 3f9d022a on GitHubtest(#682): failing — callers counts trailing-comment mentions as call sitClaude Code
  • 3ad28b28 on GitHubdocs(changelog): 0.2.5825 — full measured perf numbers (hot path 4-8x, loaDevin
  • 9b3f9dca on GitHubchore(release): 0.2.5825 — version bump + changelog for the perf/correctneDevin
  • a8a37974 on GitHubperf(search): reconcile skip_trigram_files with disk-loaded trigram indexeDevin
  • e37a6352 on GitHubfix(#692): skip .devenv and .jj by defaultCursor Agent
  • 1d468f73 on GitHubtest(#692): .devenv and .jj must not be indexedCursor Agent
  • d1b2be85 on GitHubfix(#694): compile FileChangeWatch on WindowsCursor 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 window1,137
Merge commits removed−251
CI / dependency bots removed−0
Considered886

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →Devin commitsBrowse repositories with detected Devin 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 justrach/codedb

Scan another repository

Try