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.

Orchestration-builder SDK for multi-agent coding workflows

01Result

gastownhall/gascity ↗

gastownhall/gascity AI coding statistics: 48.7%

of 5,659 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
48.7% agent · top contributor 39.3%129 contributors
org-wide

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

2,756
agent commits
2,903
other considered commits
129
agent contributors
39.3%
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

2755assisted
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.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-02100%311
2026-0377.8%1027
2026-0424.2%1135
2026-0527.6%919
2026-0660.4%820
2026-0743.1%693
2026-0844.7%481
2026-0939.6%273

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

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic274648.5%
GitHub CopilotGitHub90.2%
OpenAI CodexOpenAI10%
Cursor AgentAnysphere10%

03Evidence

Inspect the matches

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

Matched commit samples

  • 9700d9a4 on GitHubfix(workflow): refuse a workflow delete that would strand live steps (#580Claude Code
  • 2d4169ed on GitHubfix(formula): tell review-quorum workers not to poison success closes withClaude Code
  • e09602f4 on GitHubfix(hook): read each ephemeral scan once per query, not once per identity Claude Code
  • d0f66521 on GitHubHarden `make install-tools` against transient `go install` proxy failures GitHub Copilot
  • e7701ccd on GitHubAlign cmd/gc order tests with qualified `gastown.dog` pool fixtures (#2039GitHub Copilot
  • 9f954698 on GitHubStabilize `cmd/gc` imported-pack pool resolution tests to eliminate TempDiGitHub Copilot
  • 8afc5d39 on GitHubfix(gc): fall back to default nudge for stalled pool claims (#5227)OpenAI Codex
  • 1e8f5ce7 on GitHubfix(usage): settle keyless Claude ambiguous transcript misses (#5031)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 window6,124
Merge commits removed−454
CI / dependency bots removed−11
Considered5,659

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 →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 →Go AI coding statisticsCompare evidence across Go 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 gastownhall/gascity

Scan another repository

Try