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.

RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.

01Result

alibaba/rtp-llm ↗

alibaba/rtp-llm AI coding statistics: 8.2%

of 718 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

8.2% agent · top contributor 28.8%21 contributors

org-wide

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

agent commits

659

other considered commits

agent contributors

28.8%

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

59assisted

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

Peak month: 22.9%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	55	7.7%
Cursor Agent	Anysphere	3	0.4%
GitHub Copilot	GitHub	1	0.1%

03Evidence

Inspect the matches

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

Matched commit samples

b7a54379 on GitHubfeat(trace): end-to-end OpenTelemetry request tracing (#1341)Claude Code
32ecbaf1 on GitHubfeat: fix XQA CUDA graph support and enable adaptive multi-block decodeClaude Code
ea8a80a1 on GitHubfix(rocm/trt-allreduce): restore fast-path zero-copy IPC + keep exit barriClaude Code
a5701889 on GitHubfix/embedding task reuse grpc channel pool (#1368)Cursor Agent
00ace22a on GitHubfix(dash_sc): harden frontend integrationCursor Agent
4c8e6676 on GitHubfeat(logits_processor): robust prefix-dict SAX parsing and DFA error handlCursor Agent
d1a376cc on GitHubfix - test CUDA_HOMEGitHub 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 window	718
Merge commits removed	−0
CI / dependency bots removed	−0
Considered	718

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 →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 alibaba/rtp-llm

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	0%	81
2026-03	2.4%	206
2026-04	16%	188
2026-05	22.9%	70
2026-06	9.6%	52
2026-07	1.3%	78
2026-08	3.7%	27
2026-09	6.3%	16