Data and AI instructions files

774 tagged Data and AI, measured the same way as everything else here.

Browse within: machine-learning 17model-context-protocol 17knowledge-graph 16ollama 16knowledge-base 15prompt-engineering 14azure 13embeddings 13gemini 12github-copilot 12openai 12copilot 11data-engineering 10agentic-workflow 9

ruby_llm CLAUDE.md

25

crmne/ruby_llm

Instructions file

Claude Code instructions for crmne/ruby_llm, a project described as: One delightful Ruby framework for every major AI provider. Build AI agents, chatbots, RAG apps, and multimodal workflows in beautiful, expressive code.

not rated 4.3k +7 2d ago A 5 tokens copy · 100% MIT

modlens AGENTS.md

26

liustack/modlens

Instructions file CodexOpenCode

AGENTS.md instructions for liustack/modlens, covering project overview (for ai agent), goal, scope, technical approach and code organization.

not rated 3.8k +56 2d ago A 1,760 tokens original MIT

NVIDIA/Model-Optimizer

Instructions file CodexOpenCode ✓ vendor

AGENTS.md instructions for NVIDIA/Model-Optimizer, covering agent instructions for modelopt, repository orientation, coding guidelines, iterative development and contributing and pr readiness.

not rated 3.7k +63 yesterday A 920 tokens original Apache-2.0

NVIDIA/Model-Optimizer

Instructions file ✓ vendor

Claude Code instructions for NVIDIA/Model-Optimizer, a project described as: A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like…

not rated 3.7k +63 yesterday A 3 tokens copy · 100% Apache-2.0

modelscope/evalscope

Instructions file GitHub Copilot

Copilot instructions for modelscope/evalscope, a project described as: A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.

not rated 3.3k +13 2d ago A 4 tokens copy · 100% Apache-2.0

evalscope AGENTS.md

30

modelscope/evalscope

Instructions file CodexOpenCode

AGENTS.md instructions for modelscope/evalscope, covering agents.md, setup, build, lint, test, docs generation and quick eval.

not rated 3.3k +13 changed yesterday A 2,880 tokens original Apache-2.0

marin AGENTS.md

31

marin-community/marin

Instructions file CodexOpenCode

AGENTS.md instructions for marin-community/marin, covering agent guidelines for marin, operational guides, infrastructure (pulumi), workflow playbooks and handle requests.

not rated 3.2k +173 yesterday A 2,840 tokens original Apache-2.0

simonlin1212/TradingAgents-astock

Instructions file

Project instructions for TradingAgents-Astock, a Python system in which several AI roles examine Chinese A-share stocks, debate opposing views, and produce an investment report. It also documents the market-data sources and version files.

not rated 3.1k +16 changed yesterday A 3,359 tokens original Apache-2.0

spiceai CLAUDE.md

33

spiceai/spiceai

Instructions file

Claude Code instructions for spiceai/spiceai, a project described as: Add a real-time analytics node to your operational database. Spice is a portable, accelerated SQL query, search, and LLM-inference engine in Rust for data-grounded AI apps and agents.

not rated 3.1k yesterday A 6 tokens copy · 100% Apache-2.0

ax AGENTS.md

36

ax-llm/ax

Instructions file CodexOpenCode

AGENTS.md instructions for ax-llm/ax, covering ax repository guide, what this file is for, repository layout, canonical docs and current project defaults.

not rated 2.9k +2 2d ago A 1,548 tokens original Apache-2.0

jgravelle/jcodemunch-mcp

Instructions file CodexOpenCode

AGENTS.md instructions for jgravelle/jcodemunch-mcp, covering code exploration policy, session-aware routing and model-driven tool tiering.

not rated 2.6k +8 today A 1,312 tokens

plexe CLAUDE.md

38

plexe-ai/plexe

Instructions file

Instructions for plexe-ai/plexe, a project described as: ✨ Build a machine learning model from a prompt.

not rated 2.6k +3 6mo ago A 3 tokens copy · 100% Apache-2.0

ForceInjection/AI-fundamentals

Instructions file CodexOpenCode

Instructions for an AI infrastructure learning collection covering hardware, GPU programming, cloud systems, model training, language models, retrieval, and agent systems. They describe the project's main subject areas and tools.

not rated 2.5k +30 2d ago A 792 tokens original Apache-2.0

mflux AGENTS.md

40

mflux-community/mflux

Instructions file CodexOpenCode

AGENTS.md instructions for mflux-community/mflux, a project described as: Apple MLX native implementations of state-of-the-art generative image & video models.

not rated 2.3k +2 2d ago A 23 tokens original MIT

PrismML-Eng/Bonsai-demo

Instructions file CodexOpenCode

Instructions for PrismML-Eng/Bonsai-demo, covering agent guide — tuning the bonsai demo, why the 27b models (what to show off), the models, knobs that matter (27b) and adding mcp servers.

not rated 2.3k 5d ago C 4,251 tokens original Apache-2.0

eugr/spark-vllm-docker

Instructions file CodexOpenCode

Instructions for eugr/spark-vllm-docker, covering agent instructions, repository, choose one guide and common boundaries.

not rated 2.2k 7d ago A 346 tokens original MIT

Azure/azureml-examples

Instructions file GitHub Copilot ✓ vendor

Instructions for Azure/azureml-examples: If a file is listed in the CODEOWNERS file with @azure/ai-platform-docs as the owner, it is owned by the AI Platform Docs team. For these files.

not rated 2.0k 8d ago A 270 tokens original MIT

microsoft/edgeai-for-beginners

Instructions file CodexOpenCode ✓ vendor

Instructions for microsoft/edgeai-for-beginners, covering agents.md, project overview, repository structure, prerequisites and required tools.

not rated 1.7k +8 9d ago C 4,929 tokens original MIT

Lynpoint/CyberVerse

Instructions file CodexOpenCode

AGENTS.md instructions for Lynpoint/CyberVerse, a project described as: Self hosted, real-time digital human agent platform. Build voice-first AI agents with WebRTC, persona memory, tools, RAG, and optional digital-human video.

not rated 1.6k +7 29d ago A 1,159 tokens GPL-3.0

ktx GEMINI.md

46

Kaelio/ktx

Instructions file Gemini CLI

Gemini CLI instructions for Kaelio/ktx, a project described as: ktx is an executable context layer for data and analytics agents 🐙 Allow Claude Code, Codex, or other AI agents to query analytical databases accurately and with full context of your company.

not rated 1.6k +3 1mo ago A 3 tokens copy · 100% Apache-2.0

microsoft/prompty

Instructions file GitHub Copilot ✓ vendor

Instructions for microsoft/prompty, covering prompty v2 — complete rebuild plan, what prompty uses from the typra-generated model, key design decisions, python coding rules and environment & tooling.

not rated 1.3k 5d ago A 14,642 tokens original MIT

Azure/GPT-RAG

Instructions file GitHub Copilot ✓ vendor

Instructions for Azure/GPT-RAG, a project described as: Sharing the learning along the way we been gathering to enable Azure OpenAI at enterprise scale in a secure manner. GPT-RAG core is a Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large…

not rated 1.2k 16d ago A 180 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: