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.

Positron, a next-generation data science IDE

01Result

posit-dev/positron ↗

posit-dev/positron AI coding statistics: 17.8%

of 1,755 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
17.8% agent · top contributor 41.7%23 contributors
org-wide

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

312
agent commits
1,443
other considered commits
23
agent contributors
41.7%
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

310assisted
2autonomous

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
2026-0216.6%211
2026-0315.4%214
2026-0421.6%208
2026-0518.8%223
2026-0617.7%299
2026-0714.5%256
2026-0820.2%257
2026-0917.2%87

Peak month: 21.6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic30017.1%
GitHub CopilotGitHub120.7%
Cursor AgentAnysphere10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • bd507276 on GitHube2e: add Snowflake catalog explorer case and run the suite on Workbench (#Claude Code
  • f7d37006 on GitHubci: skip Graphviz install and graphviz plot tests on macOS x64 (#16076)Claude Code
  • ebbac484 on GitHube2e: settle the assistant greeting before trusting a skipped new-conversatClaude Code
  • 6d3e9092 on GitHubAdd a per-license hash to P3M gallery telemetry (#15765)GitHub Copilot
  • a3a370d4 on GitHub13902 pinned columns in data explorer are painted on top of each other (#1GitHub Copilot
  • 700c2703 on GitHubImprove Assistant quick-fix attachment labels and error messages (#15286)GitHub Copilot
  • 44a420db on GitHubFeature/notebook cell tags (#14021)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 window1,866
Merge commits removed−0
CI / dependency bots removed−111
Considered1,755

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 posit-dev/positron

Scan another repository

Try