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.

The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems.

01Result

microsoft/PyRIT ↗

microsoft/PyRIT AI coding statistics: 64.1%

of 940 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
64.1% agent · top contributor 50.9%65 contributors
team

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

603
agent commits
337
other considered commits
65
agent contributors
50.9%
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

589assisted
14autonomous

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
2026-0230%50
2026-0341.1%95
2026-0452%127
2026-0571%131
2026-0682.4%159
2026-0771.9%139
2026-0873.6%148
2026-0954.9%91

Peak month: 82.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub59863.6%
Claude CodeAnthropic91%

03Evidence

Inspect the matches

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

Matched commit samples

  • b0dba3ed on GitHubFIX guard unsaved configuration changes (#2631)GitHub Copilot
  • f4de826d on GitHubFIX make file output safe across event loops (#2664)GitHub Copilot
  • cd59b78d on GitHubFIX: Treating simulated conversations properly (#2629)GitHub Copilot
  • c0bcdcad on GitHubFIX: validate BinaryConverter bit width per converted word (#2591)Claude Code
  • e85bd797 on GitHubFIX: report Unicode tag presence correctly when decoding (#2657)Claude Code
  • 509a46c9 on GitHubFIX: restore the configured separator in BinAsciiConverter all-words joinsClaude Code

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 window1,047
Merge commits removed−0
CI / dependency bots removed−107
Considered940

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 →Python AI coding statisticsCompare evidence across Python 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 microsoft/PyRIT

Scan another repository

Try