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 Datacenter Scale Distributed Inference Serving Framework

01Result

ai-dynamo/dynamo ↗

ai-dynamo/dynamo AI coding statistics: 16.6%

of 4,153 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
16.6% agent · top contributor 9.4%111 contributors
org-wide

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

690
agent commits
3,463
other considered commits
111
agent contributors
9.4%
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

689assisted
1autonomous

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
2026-0218.6%512
2026-0310%520
2026-0423.8%546
2026-0518.1%608
2026-0617.8%471
2026-0716.1%597
2026-0814.1%560
2026-0913%339

Peak month: 23.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic61214.7%
Cursor AgentAnysphere681.6%
DevinCognition100.2%
OpenAI CodexOpenAI30.1%
GitHub CopilotGitHub20%

03Evidence

Inspect the matches

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

Matched commit samples

  • f1cb3ae6 on GitHubrefactor(http): consolidate to a single aiohttp backend; remove httpx (#14Claude Code
  • d481e51e on GitHubfix(metrics): restore documented histogram bucket env var names (#14514)Claude Code
  • 28e2a555 on GitHubci(datadog): put the venv's pip on PATH so ddtrace installs (#14233)Claude Code
  • 7a3d29ac on GitHubperf(llm): share prompt tokens across request clones (#14701)Cursor Agent
  • 6e2a4618 on GitHubfeat(gms): GMS V1 refactor for vLLM + SGLang integration (#13218)Cursor Agent
  • 9352338c on GitHubfix(operator): bind DGDR profiler resources by container name in conversioCursor Agent
  • 062a4958 on GitHubfix(benchmarks): isolate router benchmark imports (#14745)Devin
  • 712d21ce on GitHubbuild(deps): upgrade AIPerf to 0.12.0 (#14492)Devin
  • ec77e53f on GitHubfeat(examples): add heterogeneous disagg serving xpu + cpu example on dynaDevin
  • a6fa367e on GitHubfeat(recipes): add A.X-K2 NVFP4 B200 serving and benchmark recipes (#14635OpenAI Codex
  • 341f9ac9 on GitHubfeat: Dynamo performance optimization agent skills (#13557)OpenAI Codex
  • b650c53e on GitHubperf(python): intern request-plane envelope keys (#11331)OpenAI Codex
  • 06fc5d5e on GitHubfeat: Make the image field optional in DGDRs (#6557)GitHub Copilot
  • d100c6e2 on GitHubfeat: use v1beta1 DGDR in controller (#6498)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 window4,160
Merge commits removed−0
CI / dependency bots removed−7
Considered4,153

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 →Devin commitsBrowse repositories with detected Devin signatures →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →Rust AI coding statisticsCompare evidence across Rust 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 ai-dynamo/dynamo

Scan another repository

Try