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.

~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.

01Result

LearningCircuit/local-deep-research ↗

LearningCircuit/local-deep-research AI coding statistics: 0.5%

of 2,425 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
0.5% agent · top contributor 27.3%8 contributors
team

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

11
agent commits
2,414
other considered commits
8
agent contributors
27.3%
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

11assisted
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
2026-010%2
2026-020.5%387
2026-030%564
2026-041.5%270
2026-050.6%351
2026-060%388
2026-071%192
2026-080%159
2026-090.9%112

Peak month: 1.5%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic70.3%
GitHub CopilotGitHub40.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • b11e2c5b on GitHubfix(tests): point unit-test profiles at the maintained Google PSE tests (#Claude Code
  • 3f7a1912 on GitHubrefactor(metrics): remove dead PricingCache disk-cache no-op stubs (#4921)Claude Code
  • 47d370c4 on GitHubfix(notifications): allow signal:// Apprise scheme (#4006) (#4056)Claude Code
  • fbdeb260 on GitHubfix(strategies): port cancellation check to 5 strategies (issue #4871) (#5GitHub Copilot
  • ccb352ed on GitHubfix(pdf): graceful degradation when WeasyPrint system libs are missing (#3GitHub Copilot
  • 913ce67d on GitHubBench/arxiv search performance (#3469)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 window3,007
Merge commits removed−42
CI / dependency bots removed−540
Considered2,425

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 LearningCircuit/local-deep-research

Scan another repository

Try