Pulse
2026-09-18-v3.0
Dataset
2026-09-18-v3.0
Ruleset
b2e8889c66f7
Scanned
2026-09-16
Window
February–September 15, 2026
Local to this browser
hiyouga/LlamaFactory ↗

hiyouga/LlamaFactory AI coding statistics: 14.6%

of 164 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
14.6% agent · top contributor 16.7%16 contributors
org-wide

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

24
agent commits
140
other considered commits
16
agent contributors
16.7%
largest contributor

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

24assisted
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. Across the whole index, 96% of agent commits are assisted.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-0216%25
2026-0310.3%29
2026-0410%20
2026-0517.4%23
2026-0613.6%22
2026-0731.8%22
2026-085.9%17
2026-090%6

Peak month: 31.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic127.3%
Gemini CLIGoogle106.1%
Cursor AgentAnysphere21.2%
GitHub CopilotGitHub10.6%

Inspect the matches

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

Matched commit samples

  • 63a89710 on GitHub[data] pad position_ids on non-FA2 packing path (fixes rotary crash for GeClaude Code
  • 62ae3624 on GitHub[v1] Support multimodal data training (#10656)Claude Code
  • 2ebe7be6 on GitHub[ci] pin ruff version and fix lint errors (#10681)Claude Code
  • b61140db on GitHub[v1] replace custom template system with apply_chat_template (#10598)Gemini CLI
  • a61cfa69 on GitHub[readme] Revise bitsandbytes installation instructions in README (#10621)Gemini CLI
  • c8a082e0 on GitHub[fix] Fixes Qwen3-VL prompt expansion for multiple videos (#10518)Gemini CLI
  • 897a4438 on GitHub[docs] add DataFlow and DataFlex blog tutorials (#10582)Cursor Agent
  • 40e786d0 on GitHub[data] add missing return statement in MiniCPM V Plugin (#10500)Cursor Agent
  • 16ff5a23 on GitHub[fix] use getattr for profiler attrs to support MCA TrainingArguments (#10GitHub Copilot

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 window164
Merge commits removed−0
CI / dependency bots removed−0
Considered164

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

Pinned to a source state

This observation names the repository state, release, and detector that produced it. Use these identifiers when reproducing or citing the result.

Dataset release
2026-09-18-v3.0
Scan date
2026-09-16
Ruleset
sha256:b2e8889c66f72c18a61839f0bf1a9f77b5481ba2def044dba33c797b2f2bdcae
Canonical repository
hiyouga/LlamaFactory
Default branch
main
Resolved
2026-09-16
Measurement window
February–September 15, 2026
Download observation JSONDeterministic export · same values as this page

Position among comparable repositories

The cohort uses the same release and measurement window, then narrows to the repository’s ecosystem and removes low-activity observations.

CohortPython · 247 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 145 of 392 ecosystem repositories excluded
Agent-commit share position71st percentile

Midrank percentile; equal shares split the tied positions.

Repository
14.6%
Cohort median
6.3%
Share rank
72 / 247
0th50th100th

Percentile = (repositories below + half of 2 tied repositories) ÷ 247.

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 hiyouga/LlamaFactory

Scan another repository