Data and AI instructions files

1,256 tagged Data and AI, measured the same way as everything else here.

Browse within: copilot 35model-context-protocol 35claude-code-plugin 28machine-learning 28azure 27openai 25knowledge-base 21ollama 20gemini 19prompt-engineering 19ai-assistant 18knowledge-graph 18embeddings 17github-copilot 17

jasonkneen/tiny-world-builder

Instructions file CodexOpenCode

AGENTS.md instructions for jasonkneen/tiny-world-builder, covering agents.md, project shape, repo-local skills, house style and mental model.

not rated 1.6k +4 today A 2,585 tokens AGPL-3.0

ai4s-research/open-science

Instructions file

Claude Code instructions for ai4s-research/open-science, a project described as: Open Science Desktop — local-first, model-agnostic AI research workbench for macOS, Windows & Linux. Open-source Claude Science desktop alternative built on Tauri + MCP + agent skills.

not rated 1.6k +33 today A 3 tokens

xllm CLAUDE.md

99

xLLM-AI/xllm

Instructions file

Claude Code instructions for xLLM-AI/xllm, a project described as: A high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators. It is hosted in OpenAtom Foundation.

not rated 1.6k changed today A 5 tokens copy · 100% Apache-2.0

gortex CLAUDE.md

100

zzet/gortex

Instructions file

Claude Code instructions for zzet/gortex, covering gortex, build & test, codebase overview, discovery (read once, then keep using) and llm provider (powers ask and searchsymbols assist: modes).

not rated 1.5k +9 today A 5,172 tokens original Apache-2.0

kotlin-sdk CLAUDE.md

101

modelcontextprotocol/kotlin-sdk

Instructions file ✓ vendor

Claude Code instructions for modelcontextprotocol/kotlin-sdk, a project described as: The official Kotlin SDK for Model Context Protocol servers and clients. Maintained in collaboration with JetBrains.

not rated 1.4k today A 3 tokens

chunkhound AGENTS.md

102

chunkhound/chunkhound

Instructions file CodexOpenCode

AGENTS.md instructions for chunkhound/chunkhound, covering chunkhound llm context, projectidentity, modificationrules, keycommands and development.

not rated 1.4k +2 today A 2,309 tokens original MIT

commonly CLAUDE.md

103

Team-Commonly/commonly

Instructions file

Claude Code instructions for Team-Commonly/commonly, covering claude.md / agents.md, 🧠 product vision & architecture philosophy, what commonly is, the architecture model and key concepts.

not rated 1.3k changed today B 16,236 tokens original Apache-2.0

raspibolt CLAUDE.md

104

raspibolt/raspibolt

Instructions file

Claude Code instructions for raspibolt/raspibolt, covering raspibolt: development guidelines, working rules, autonomy model, level 0: autonomous and level 1: inform.

not rated 1.3k today B 2,840 tokens original MIT

microsoft/prompty

Instructions file GitHub Copilot ✓ vendor

Copilot 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 yesterday A 14,642 tokens original MIT

Azure/GPT-RAG

Instructions file GitHub Copilot ✓ vendor

Copilot instructions for Azure/GPT-RAG, covering repository development and release instructions, branching strategy, default behavior, feature development workflow and branch creation.

not rated 1.2k today A 1,899 tokens original MIT

Azure/GPT-RAG

Instructions file GitHub Copilot ✓ vendor

Instructions for Azure/GPT-RAG, a project described as: Enterprise-grade accelerator for agentic RAG on Azure. Built on Microsoft Foundry with Foundry IQ as the default retrieval backend, Microsoft Agent Framework orchestration, Zero-Trust architecture and IaC.

not rated 1.2k today A 180 tokens original MIT

GPT-RAG AGENTS.md

108

Azure/GPT-RAG

Instructions file CodexOpenCode ✓ vendor

AGENTS.md instructions for Azure/GPT-RAG, covering gpt-rag agent operating contract, priority, what this repository is, repository boundaries and how to work.

not rated 1.2k today A 1,538 tokens original MIT

vndee/llm-sandbox

Instructions file GitHub Copilot

Copilot instructions for vndee/llm-sandbox, covering github copilot instructions for llm sandbox, project overview, code style and formatting, python code standards and code organization.

not rated 1.1k 2d ago A 2,205 tokens original MIT

llm-sandbox CLAUDE.md

110

vndee/llm-sandbox

Instructions file

Claude Code instructions for vndee/llm-sandbox, covering llm sandbox - ai assistant guide, project overview, core architecture, key components and project structure.

not rated 1.1k 2d ago A 2,639 tokens original MIT

K-Dense-AI/k-dense-byok

Instructions file CodexOpenCode

Instructions for K-Dense-AI/k-dense-byok, covering claude.md, project overview, commands, architecture: how a turn flows and project / sandbox layout.

not rated 1.1k +33 7d ago A 7,467 tokens original MIT

clawsec AGENTS.md

112

prompt-security/clawsec

Instructions file CodexOpenCode

AGENTS.md instructions for prompt-security/clawsec, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.

not rated 1.1k today A 1,131 tokens AGPL-3.0

clawsec CLAUDE.md

113

prompt-security/clawsec

Instructions file

Claude Code instructions for prompt-security/clawsec, covering claude.md, development setup, common commands, releasing a skill and example: ./scripts/release-skill.sh clawsec-feed 0.0.5.

not rated 1.1k today A 2,410 tokens AGPL-3.0

nnsight CLAUDE.md

114

ndif-team/nnsight

Instructions file

Instructions for ndif-team/nnsight, covering nnsight — agent guide, how to use this file, by task, "i want multi-token / autoregressive generation" and "i want to run multiple prompts at once".

not rated 1.1k 6d ago A 3,828 tokens original MIT

QueryWeaver AGENTS.md

115

FalkorDB/QueryWeaver

Instructions file CodexOpenCode

AGENTS.md instructions for FalkorDB/QueryWeaver, covering agents.md — queryweaver (text2sql), project overview, tech stack, directory structure and quick reference.

not rated 1.1k 4d ago A 1,467 tokens AGPL-3.0

QueryWeaver CLAUDE.md

116

FalkorDB/QueryWeaver

Instructions file

Claude Code instructions for FalkorDB/QueryWeaver, a project described as: An open-source Text2SQL tool that transforms natural language into SQL using graph-powered schema understanding. Ask your database questions in plain English, QueryWeaver handles the weaving.

not rated 1.1k 4d ago A 3 tokens AGPL-3.0

tracer AGENTS.md

117

adrida/tracer

Instructions file CodexOpenCode

Instructions for adrida/tracer, covering can i install it without asking?, the 4 things tracer does, 1. fit - learn a routing policy from teacher traces, 2. route - predict with the surrogate or defer to teacher and 3. update - continual learning (coverage grows over time).

not rated 1.0k +2 9d ago A 1,842 tokens original MIT

duanyytop/agents-radar

Instructions file CodexOpenCode

AGENTS.md instructions for duanyytop/agents-radar, covering agents.md, project overview, commands, llm provider (default: anthropic) and anthropic (default).

not rated 1.0k yesterday A 2,780 tokens original MIT

duanyytop/agents-radar

Instructions file

Claude Code instructions for duanyytop/agents-radar, covering claude.md, project overview, commands, llm provider (default: anthropic) and anthropic (default).

not rated 1.0k changed today A 4,299 tokens original MIT

agentsys CLAUDE.md

120

agent-sh/agentsys

Instructions file

Claude Code instructions for agent-sh/agentsys, covering agentsys, critical rules, model selection, core priorities and dev commands.

not rated 982 +2 7d ago A 360 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: