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.

High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle

01Result

PaddlePaddle/FastDeploy ↗

PaddlePaddle/FastDeploy AI coding statistics: 5%

of 844 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
5% agent · top contributor 21.4%22 contributors
org-wide

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

42
agent commits
802
other considered commits
22
agent contributors
21.4%
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

42assisted
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
2026-024.7%148
2026-037.9%252
2026-044.3%230
2026-054.1%121
2026-060%69
2026-070%15
2026-080%9

Peak month: 7.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic293.4%
GitHub CopilotGitHub141.7%
OpenAI CodexOpenAI10.1%
Cursor AgentAnysphere10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • a9186935 on GitHub[Metric] Support custom metric labels (#7865)Claude Code
  • d31ebcce on GitHub[Feature] Support NaiveProposer for most cases (#7669)Claude Code
  • 62afcc90 on GitHub[KVCache][BugFix] fix cache_manager_v1 + enable_mm crash: use in-place sorClaude Code
  • 67018867 on GitHub[Speculative Decoding]【Hackathon 10th Spring No.54】hybrid_mtp_ngram 端到端验证 GitHub Copilot
  • ec697aba on GitHub[Docs] Update router launch docs to use Python CLI (fastdeploy.golang_routGitHub Copilot
  • df594a17 on GitHub[Feature] Support launching golang-router via python -m command (#7668)GitHub Copilot
  • 42dbd1fe on GitHub[GPU][CI] Guard SM90 pybind bindings (#7925)OpenAI Codex
  • aae87e6a on GitHub[CI] 【Hackathon 10th Spring No.27】功能模块 fastdeploy/cache_manager/prefix_cacCursor 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 window844
Merge commits removed−0
CI / dependency bots removed−0
Considered844

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex 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 PaddlePaddle/FastDeploy

Scan another repository

Try