Data and AI

3,706 projects whose own agent configuration covers data and ai. These are not mods to install — they are how the maintainers of these repositories tell an agent what to do, and what to avoid.

All projects Building agents7,374Claude Code6,573Backend and APIs3,486Languages3,398Planning3,181Git and workflow3,100Code review2,701Memory and context2,354Testing2,311Research2,292DevOps and cloud2,282Writing and docs2,269

Any agent Claude CodeCodexOpenCodeGitHub CopilotGemini CLICursorWindsurfKiro

ProjectStarsConfiguresFilesAlways loaded
fluxions-ai/vui fluxions.ai Real-time voice assistant — WebRTC streaming, faster-whisper ASR, local LLM, Vui Nano (300 757 Codex, OpenCode 1 2,201 tok
FrancescoStabile/numasec The AI Agent for Cyber Security. 754 Codex, OpenCode 1 2,610 tok
Warma10032/VideoAdGuard videoadguard.xiaobaozi.cn A Bilibili browser extension that uses large language models to detect embedded advertisem 751 Claude Code 1 1,513 tok
cardmagic/classifier A general classifier module to allow Bayesian and LSI classifications. 741 Claude Code, Codex, OpenCode 3 1,005 tok
huggingface/upskill Generate and evaluate agent skills for code agents like Claude Code, Open Code, OpenAI Cod 741 Codex, OpenCode 1 443 tok
GarethManning/education-agent-skills garethmanning.com 165 evidence-grounded AI skills for teachers, school leaders and EdTech builders—pedagogy, 741 Claude Code, Codex, OpenCode 2 1,127 tok
dragon1086/prism-insight prism-insight-landing.vercel.app AI-based stock analysis and trading system 737 Claude Code, Codex, OpenCode 2 5,584 tok
symgraph/GhidrAssistMCP An native MCP server extension for Ghidra 736 Claude Code 1 1,019 tok
ZeroLeaks/zeroleaks zeroleaks.ai AI Security Scanner - Test your AI systems for prompt injection and extraction vulnerabili 732 Codex, OpenCode 1 2,649 tok
memex-lab/memex memexlab.ai Open-source, local-first AI journal app for iOS and Android. Capture text, photos, and voi 720 Claude Code, Codex, GitHub Copilot, Gemini CLI, OpenCode 4 4,568 tok
neonwatty/meme-search neonwatty.github.io The open source Meme Search Engine and Finder. Free and built to self-host locally with P 719 Claude Code 1 2,697 tok
hailo-ai/hailo_model_zoo The Hailo Model Zoo includes pre-trained models and a full building and evaluation environ 704 Claude Code 3
gmickel/flow-next flow-next.dev Repeatable agentic engineering. The workflow layer that turns AI coding agents into a disc 691 Claude Code, Codex, OpenCode 3 1,091 tok
DataScienceUIBK/Rankify rankify.readthedocs.io 🔥 Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmen 682 Cursor 1 1,099 tok
arcjet/arcjet-js arcjet.com Runtime security for AI apps and agents: prompt injection detection, tool-call authorizati 682 Codex, OpenCode 1 452 tok
adhikasp/mcp-client-cli A simple CLI to run LLM prompt and implement MCP client. 677 Codex, OpenCode 1 1,472 tok
eunomia-bpf/agentsight eunomia.dev lightweight system-level observability for AI Agents 676 Claude Code, Codex, OpenCode 2 2,528 tok
teilomillet/gollm docs.gollm.co Unified Go interface for Language Model (LLM) providers. Simplifies LLM integration with f 674 Codex, OpenCode 1 294 tok
rusiaaman/wcgw Shell and coding agent on mcp clients 673 Claude Code 1 451 tok
Bessouat40/RAGLight raglight.mintlify.app RAGLight is a modular framework for Retrieval-Augmented Generation (RAG). It makes it easy 673 Claude Code 1 983 tok
usemoss/moss moss.dev The retrieval layer for production AI systems. Lightning-fast (<10ms) search without vecto 671 Claude Code, Codex, OpenCode 2 4,239 tok
duriantaco/skylos skylos.dev Open source local-first PR scanner that finds dead code, security bugs, secrets, quality r 671 Claude Code, Codex, OpenCode 4 1,138 tok
typedef-ai/fenic fenic.ai Semantic DataFrames for humans and agents 670 Claude Code, Codex, OpenCode 6 1,834 tok
swarmclawai/swarmclaw swarmclaw.ai Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent sw 665 Claude Code 1 3,713 tok
joelhooks/pdf-brain 🧠 Local PDF knowledge base with vector search using libsql w/vectors 654 Codex, OpenCode 1 531 tok
universal-tool-calling-protocol/python-utcp utcp.io Official python implementation of UTCP. UTCP is an open standard that lets AI agents call 646 Claude Code 1 871 tok
sandbaseai/sandbase-harness Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, 641 Codex, OpenCode 1 1,731 tok
zavora-ai/adk-rust adk-rust.com Rust Agent Development Kit (ADK-Rust): Build AI agents in Rust with modular components for 639 Codex, OpenCode 1 12,794 tok
genomoncology/biomcp biomcp.org BioMCP: Biomedical Model Context Protocol 628 Codex, OpenCode 1 757 tok
kiwifs/kiwifs docs.kiwifs.com Markdown filesystem for agents and teams. 624 Codex, OpenCode 1 1,245 tok
apache/casbin-gateway caswaf.org Casbin AI & MCP security gateway for HTTP, online demo: https://door.caswaf.com 620 Claude Code, Codex 1 134 tok
daydreamsai/daydreams docs.daydreams.systems Daydreams is a set of tools for building agents for commerce 617 Claude Code 1 2,281 tok
yoosuf/Messenger yoosuf.me Relational messaging database schema for one-to-one and group chat apps with attachments a 613 Claude Code, Codex, GitHub Copilot, OpenCode 3 805 tok
Lightning-AI/litData Speed up model training by fixing data loading. 613 Claude Code 1
Cjbuilds/Codex-Orchestration Bring any model to Codex, assign them any role, use them in /goal or any workflow. 612 Codex, OpenCode 1 137 tok
syi0808/screenize syi0808.github.io (Development of Screenize is currently paused) Open-source macOS screen recording app with 602 Claude Code, Codex, OpenCode 7 3,521 tok
scanaislop/aislop scanaislop.com Catch and fix the code-quality issues AI coding agents leave behind - dead code, unsafe ca 599 Claude Code, Codex, Gemini CLI, OpenCode 3 1,795 tok
Zhou-Shilin/Aether aether.baimoqilin.com A stunning, localized, general-purpose AI Agent for Android, iOS & Mac. | Aether 扶摇 597 Codex, OpenCode 1 937 tok
ggozad/haiku.rag ggozad.github.io Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and mul 596 Claude Code 2
sou350121/VLA-Handbook This project provides a comprehensive Chinese, practical learning and interview handbook f 596 Claude Code, Codex, OpenCode 2 9,205 tok
second-state/echokit_server echokit.dev Open Source Voice Agent Platform 592 Claude Code 1
allenai/vla-evaluation-harness allenai.github.io One framework to evaluate any VLA model on any robot simulation benchmark. 591 Claude Code 4 1,298 tok
openstory-so/openstory openstory.so Open-source AI-powered video sequence platform built with TanStack Start 587 Claude Code, Codex 13 13,243 tok
winstonkoh87/Athena-Public winstonkoh87.com Athena is a local-first agentic PKM that helps you make better decisions with your own con 585 Claude Code, Codex, OpenCode 6 4,355 tok
redai-infra/Relax redai-infra.github.io An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale 580 Claude Code, Codex, OpenCode 8 2,533 tok
KeyValueSoftwareSystems/agent-opfor Open-source adversary emulation for AI agents and MCP servers. 577 Claude Code, Codex, OpenCode 2 8,568 tok
hewliyang/office-agents Agent plugins for Microsoft Office but BYOK for any model and provider 573 Codex, OpenCode 1 2,643 tok
OpenYSM/YSMParser ysm.rip A Parser to recover Yes-Steve-Model Encrypted Binaries. 573 Codex, OpenCode 1 1,345 tok
green-dalii/obsidian-llm-wiki llmwiki.greenerai.top Karpathy's LLM Wiki implementation plugin for Obsidian - turns notes and PDFs into a linke 571 Claude Code, Codex, OpenCode 2 7,934 tok
Azure-Samples/aisearch-openai-rag-audio azure.microsoft.com A simple example implementation of the VoiceRAG pattern to power interactive voice generat 564 Codex, OpenCode 1 3,306 tok