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

01Result

infiniflow/ragflow ↗

infiniflow/ragflow AI coding statistics: 4.5%

of 4,102 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
4.5% agent · top contributor 15.6%62 contributors
org-wide

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

186
agent commits
3,916
other considered commits
62
agent contributors
15.6%
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

186assisted
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
2026-023%167
2026-033.9%282
2026-044.4%361
2026-056.6%458
2026-069.5%589
2026-074.1%812
2026-083%1009
2026-091.2%424

Peak month: 9.5%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic1353.3%
Cursor AgentAnysphere401%
GitHub CopilotGitHub90.2%
OpenAI CodexOpenAI20%
Other / generic agentVarious20%

03Evidence

Inspect the matches

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

Matched commit samples

  • a3b39845 on GitHubfeat(web/switch): allow dot-notation field paths in Switch condition (#142Claude Code
  • c44e171d on GitHubfeat(agent): add Sofya search tool (#19323)Claude Code
  • a2f3b5f8 on GitHubfix(web): load chunk method example images from remote repo (#19328)Claude Code
  • 38230c45 on GitHubfeat(llm): forward OpenAI user on embedding and parse requests (#19065)Cursor Agent
  • 9214b9c3 on GitHubfix(agent): allow deleting edges inside iteration on canvas (#16925)Cursor Agent
  • abdabf88 on GitHubfix(rag): key Infinity field_map by original column names, not pinyin (#18Cursor Agent
  • 9e913c3f on GitHubFix empty Markdown document parsing (#18503)GitHub Copilot
  • 776b9371 on GitHubfix(nlp): drop dead `re.I` from delimiter finditer calls (#17386)GitHub Copilot
  • 8a3699fa on GitHubfix(agent): clear component inputs on canvas re-run (#16790)GitHub Copilot
  • f420e47f on GitHubfix(ollama): preserve multimodal images (#17663)OpenAI Codex
  • 1b5ce4c2 on GitHubdocs(api): use dataset_id in retrieval example (#17662)OpenAI Codex
  • e961ef04 on GitHubfix: avoid duplicating video descriptions during parsing (#16847)Other / generic agent
  • eeb59ec4 on GitHubfeat(stt): support Fun-ASR-Flash in Tongyi-Qianwen provider (#16844)Other / generic 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 window4,137
Merge commits removed−0
CI / dependency bots removed−35
Considered4,102

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

05Provenance

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
infiniflow/ragflow
Default branch
main
Resolved HEAD
0b7dd3720a72d5d42c5dfe50b78713fe9b6f83b2 ↗
Resolved
2026-09-16
Measurement window
February–September 15, 2026
Download observation JSONDeterministic export · same values as this page

06Peer context

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.

CohortGo · 132 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 62 of 194 ecosystem repositories excluded
Agent-commit share position60th percentile

Midrank percentile; equal shares split the tied positions.

Repository
4.5%
Cohort median
2.8%
Share rank
54 / 132
0th50th100th

Percentile = (repositories below + half of 1 tied repository) ÷ 132.

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →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 infiniflow/ragflow

Scan another repository

Try