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.

NeMo Retriever Library is a scalable, performance-oriented document content and metadata extraction microservice. NeMo Retriever Library uses specialized NVIDIA NIM microservices to find, contextualize, and extract text, tables, charts and images that you can use in downstream generative applications.

01Result

NVIDIA/NeMo-Retriever ↗

NVIDIA/NeMo-Retriever AI coding statistics: 5.1%

of 762 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

5.1% agent · top contributor 28.2%9 contributors

org-wide

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

agent commits

723

other considered commits

agent contributors

28.2%

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

39assisted

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: 17.9%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	26	3.4%
Cursor Agent	Anysphere	13	1.7%

03Evidence

Inspect the matches

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

Matched commit samples

6a1fc559 on GitHubReorg/bucketize (#2215)Claude Code
e07363d5 on GitHubsimplify NIM links on prerequisites & support matrix page (#1971)Claude Code
505170f9 on GitHub(lib) Add support for vLLM-backed text/VL embedder (#1494)Claude Code
f1b2407b on GitHubfix(helm): break the split-topology gateway readiness deadlock (#2556)Cursor Agent
4d9d0d65 on GitHubUpdate Helm chart and Docker Compose to combined object-detection NIM and Cursor Agent
20420ba3 on GitHubchore: remove unused INGEST_DISABLE_DYNAMIC_SCALING references (#2382)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 window	784
Merge commits removed	−0
CI / dependency bots removed	−22
Considered	762

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 →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 NVIDIA/NeMo-Retriever

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	7.9%	63
2026-03	2.1%	145
2026-04	17.9%	95
2026-05	6.3%	142
2026-06	1.8%	56
2026-07	4.9%	61
2026-08	0.7%	151
2026-09	0%	49