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 powerful meta-prompting, context engineering and spec-driven development system that enables agents to work for long periods of time autonomously without losing track of the big picture

01Result

open-gsd/gsd-pi ↗

open-gsd/gsd-pi AI coding statistics: 26.2%

of 3,073 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
26.2% agent · top contributor 47.8%16 contributors
org-wide

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

805
agent commits
2,268
other considered commits
16
agent contributors
47.8%
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

805assisted
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
2026-0549.1%530
2026-0631.2%1169
2026-0715.9%866
2026-084.7%359
2026-0916.8%149

Peak month: 49.1%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Cursor AgentAnysphere56118.3%
Claude CodeAnthropic2417.8%
GitHub CopilotGitHub30.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 8224ca90 on GitHubdocs: resolve stabilization-plan merge conflict markersCursor Agent
  • 1990a8b4 on GitHubRe-enable ADR-045 stale-render detection via projection driftCursor Agent
  • 8bd0ba34 on GitHubfix(wave8): import deriveSliceScope for local auto-prompts useCursor Agent
  • 5f08fff5 on GitHubfix(gsd): prevent persistent auto-mode wedges (#1673)Claude Code
  • 6aea68bc on GitHubfix(gsd): make auto mode complete a milestone end to end (#1605)Claude Code
  • 87682acd on GitHubtest(pi-ai): pin Muse Spark 1.1 in the generated catalogClaude Code
  • ff928b39 on GitHubfix(gsd): restore workflow MCP transport gate for scoped runtime toolsGitHub Copilot
  • 304fb50c on GitHubFix enabled count to respect enabled settingGitHub Copilot
  • c33d5a9d on GitHubPotential fix for pull request finding 'CodeQL / Incorrect suffix check'GitHub Copilot

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 window4,114
Merge commits removed−990
CI / dependency bots removed−51
Considered3,073

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 →TypeScript AI coding statisticsCompare evidence across TypeScript 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 open-gsd/gsd-pi

Scan another repository

Try