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 framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.

01Result

microsoft/agent-framework ↗

microsoft/agent-framework AI coding statistics: 43.2%

of 1,716 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
43.2% agent · top contributor 23%69 contributors
org-wide

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

742
agent commits
974
other considered commits
69
agent contributors
23%
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

714assisted
28autonomous

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
2026-0237.1%237
2026-0357.7%208
2026-0444.4%178
2026-0544.5%209
2026-0657.4%235
2026-0733.5%257
2026-0827.4%175
2026-0942.9%217

Peak month: 57.7%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub72442.2%
Claude CodeAnthropic191.1%
Cursor AgentAnysphere10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 6ad7ba2f on GitHubPython/.NET: verify supplied MCP skill archive digests (#8404)GitHub Copilot
  • 301a4ae3 on GitHub.NET: Preserve hosted session key boundaries (#8263)GitHub Copilot
  • 5ce7f36b on GitHubPython: Propagate runtime arguments to skill callbacks (#8387)GitHub Copilot
  • cd9f4cc5 on GitHubPython: drop continuation_token after a resumed background stream completeClaude Code
  • 43e4b6a4 on GitHubPython: fix: keep AG-UI workflow reasoning in thread snapshots (#8058)Claude Code
  • 41e3c602 on GitHubPython: [BREAKING] Add file_access_read_lines and move the line-numbering Claude Code
  • 13fc425b on GitHubPython: docs: fix removed ChatAgent references in _clients.py docstrings (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 window1,816
Merge commits removed−0
CI / dependency bots removed−100
Considered1,716

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 →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/agent-framework

Scan another repository

Try