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 deep learning package for many-body potential energy representation and molecular dynamics

01Result

deepmodeling/deepmd-kit ↗

deepmodeling/deepmd-kit AI coding statistics: 6.4%

of 406 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
6.4% agent · top contributor 23.1%10 contributors
org-wide

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

26
agent commits
380
other considered commits
10
agent contributors
23.1%
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

26assisted
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
2026-0220%45
2026-030%46
2026-048.1%37
2026-058.7%23
2026-067.6%79
2026-072.3%131
2026-080%33
2026-0925%12

Peak month: 25%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub194.7%
Claude CodeAnthropic61.5%
Gemini CLIGoogle20.5%
Cursor AgentAnysphere10.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • b255998e on GitHubfix(pd): add default chg spin parameter (#5469)GitHub Copilot
  • a49b6f79 on GitHubadd DPA-ADAPT toolkit for downstream property adaptation (#5572)GitHub Copilot
  • 5e80487f on GitHubfeat(core): batch prod env mat over frames (#5582)GitHub Copilot
  • 0192667f on GitHubfix(pair-tab): validate uniform distance grid to avoid silently wrong poteClaude Code
  • 1c23cb59 on GitHubfeat(pt,pd): exact full-scan output statistics via streaming QR (#6011)Claude Code
  • 480509aa on GitHubperf(pt): DPA4-family performance optimizations (#6001)Claude Code
  • 09e40bbf on GitHubfeat(pt): add FSDP & ZeRO1 (Zero Redundancy Optimizer) support (#5222)Gemini CLI
  • 29014480 on GitHubrefact(pt_expt): add decorator to simplify the module (#5213)Gemini CLI
  • dbdc9a3e on GitHubfeat(pt): add atomic charge population fitting and model (#5494)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 window458
Merge commits removed−1
CI / dependency bots removed−51
Considered406

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 →Gemini CLI commitsBrowse repositories with detected Gemini CLI 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 deepmodeling/deepmd-kit

Scan another repository

Try