Data and AI

3,584 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 agents8,442Claude Code6,875Git and workflow3,574Backend and APIs3,550Languages3,468Planning3,315Code review2,876Testing2,653DevOps and cloud2,462Writing and docs2,461Memory and context2,373Research2,315

Any agent Claude CodeCodexOpenCodeGitHub CopilotGemini CLICursorWindsurfKiro

ProjectStarsConfiguresFilesAlways loaded
DataScienceUIBK/Rankify rankify.readthedocs.io 🔥 Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmen 683 Cursor 1 1,099 tok
typedef-ai/fenic fenic.ai Semantic DataFrames for humans and agents 679 Claude Code, Codex, OpenCode 6 1,834 tok
rusiaaman/wcgw Shell and coding agent on mcp clients 678 Claude Code 1 451 tok
adhikasp/mcp-client-cli A simple CLI to run LLM prompt and implement MCP client. 676 Codex, OpenCode 1 1,472 tok
teilomillet/gollm docs.gollm.co Unified Go interface for Language Model (LLM) providers. Simplifies LLM integration with f 675 Codex, OpenCode 1 294 tok
Bessouat40/RAGLight raglight.mintlify.app RAGLight is a modular framework for Retrieval-Augmented Generation (RAG). It makes it easy 672 Claude Code, Codex, OpenCode 2 1,305 tok
universal-tool-calling-protocol/python-utcp utcp.io Official python implementation of UTCP. UTCP is an open standard that lets AI agents call 665 Claude Code 1 871 tok
joelhooks/pdf-brain 🧠 Local PDF knowledge base with vector search using libsql w/vectors 664 Codex, OpenCode 1 531 tok
lynote-ai/ai-text-detector lynote.ai A cautious, explainable AI text detector for local workflows and coding agents. Need produ 657 Claude Code, Codex, OpenCode 2 212 tok
ggozad/haiku.rag ggozad.github.io Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and mul 650 Claude Code, Codex, OpenCode 4 25,097 tok
apache/casbin-gateway gateway.casbin.org See what every AI coding agent on your machine is doing, and whether the API behind it is 647 Claude Code 1 134 tok
sandbaseai/sandbase-harness Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, 640 Codex, OpenCode 1 1,969 tok
Cjbuilds/Codex-Orchestration Bring any model to Codex, assign them any role, use them in /goal or any workflow. 634 Codex, OpenCode 1 137 tok
daydreamsai/daydreams docs.daydreams.systems Daydreams is a set of tools for building agents for commerce 624 Claude Code 1 2,281 tok
zosmaai/pi-llm-wiki zosmaai.github.io Self-maintaining, Obsidian-compatible knowledge base for pi — turn raw sources into an int 623 Codex, OpenCode 1 594 tok
metadist/synaplan synaplan.com Open-source, self-hosted AI platform (PHP/Symfony): chat with any model, RAG over your doc 622 Codex, OpenCode 1 2,884 tok
winstonkoh87/Athena-Public winstonkoh87.com Local-first memory, decision engine, and governance harness for AI agents — portable acros 620 Claude Code, Codex, OpenCode 6 4,777 tok
syi0808/screenize syi0808.github.io (Development of Screenize is currently paused) Open-source macOS screen recording app with 619 Claude Code, Codex, OpenCode 7 3,521 tok
NVIDIA/cosmos-framework nvidia.github.io Our inference and training framework to run on the Cosmos Models 618 Claude Code, Codex, OpenCode 17 2,061 tok
Lightning-AI/litData Speed up model training by fixing data loading. 617 Claude Code 1 —
aisa-group/PostTrainBench posttrainbench.com Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a 612 Claude Code, Codex, OpenCode 2 8,763 tok
yoosuf/Messenger yoosuf.me Relational messaging database schema for one-to-one and group chat apps with attachments a 609 Claude Code, Codex, GitHub Copilot, OpenCode 3 805 tok
hewliyang/office-agents Agent plugins for Microsoft Office but BYOK for any model and provider 596 Codex, OpenCode 1 2,643 tok
second-state/echokit_server echokit.dev Open Source Voice Agent Platform 590 Claude Code 1 —
KeyValueSoftwareSystems/agent-opfor Open-source adversary emulation for AI agents and MCP servers. 584 Claude Code, Codex, OpenCode 2 8,568 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
microsoft/DebugMCP Gift your VS Code agent a real debugger: breakpoints, stepping, inspection. 579 Codex, OpenCode 1 970 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
VSLAM-LAB/VSLAM-LAB A Comprehensive Framework for Visual SLAM Systems and Datasets 569 Claude Code 6 2,261 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
miantiao-me/aigc-weekly aigc-weekly.agi.li Agili's AIGC Weekly — a curated AIGC (artificial intelligence-generated content) newslette 563 Claude Code, Codex, OpenCode 2 1,281 tok
Muvon/octomind octomind.run Open-source AI coding agent and agent runtime: one binary, any model, MCP-native. Runs in 563 Codex, OpenCode 1 4,151 tok
freddy-schuetz/n8n-claw n8n-claw.com OpenClaw-inspired autonomous AI agent built entirely in n8n. Adaptive RAG-powered memory, 561 Claude Code 1 6,906 tok
antgroup/agentic-ai-landscape insights.inclusion-ai.org Data driven agentic landscapes and insights. Produced by Ant Open Source and inclusionAI. 560 Claude Code, Codex, OpenCode 2 3,728 tok
giselles-ai/giselle giselles.ai Giselle: AI App Builder. Open Source. 559 Claude Code, Codex, OpenCode 10 2,832 tok
deerwork-ai/deer-workflow deerwork-ai.github.io An open-source graph engineering runtime that keeps orchestration in TypeScript and delega 556 Claude Code, Codex, OpenCode 2 4,147 tok
caura-ai/caura caura.ai Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi- 549 Claude Code 2 —
thiswillbeyourgithub/wdoc wdoc.readthedocs.io Summarize and query from a lot of heterogeneous documents. Any LLM provider, any filetype, 549 Claude Code 1 2,156 tok
esbmc/esbmc esbmc.org The efficient SMT-based context-bounded model checker (ESBMC) 543 Claude Code, Codex, GitHub Copilot, OpenCode 4 3,525 tok
XPolicyLab/XPolicyLab xpolicylab.github.io [IROS 26 ScaleInfra Workshop Best Tool Paper] Involving over 50 Advanced Manipulation Poli 538 Claude Code, Codex, OpenCode 4 1,573 tok
allenhutchison/obsidian-gemini allenhutchison.github.io An obsidian plugin to interact with Google Gemini 534 Claude Code, Codex, Gemini CLI, OpenCode 11 9,622 tok
chrisdoc/hevy-mcp hevy-mcp.dev Manage your Hevy workouts, routines, folders, and exercise templates. Create and update se 533 Claude Code, Codex, OpenCode 2 2,200 tok
lambda-symbolics/autolith lambda-symbolics.com Autolith is a self-modifiable general purpose Lisp AI agent 533 Codex, OpenCode 1 4,920 tok
Muvon/octocode octomind.run Structural code intelligence for AI agents — semantic search, knowledge graphs, and a buil 522 Codex, OpenCode 1 1,909 tok
meleantonio/ChernyCode 520 Claude Code, Codex, Cursor, OpenCode 10 1,022 tok
antgroup/vsag vsag.io vsag is a vector indexing library used for similarity search. 516 Claude Code, Codex, GitHub Copilot, OpenCode 4 1,535 tok
BrowserOperator/browser-operator-core browseroperator.io Browser Operator - The AI browser with built in Multi-Agent platform! Open source alternat 514 Claude Code 1 1,984 tok
Deuz-AI/Deuz-SDK deuz-sdk.tech TypeScript AI SDK and agent framework with zero dependencies. Build production AI agents a 508 Claude Code 1 —
Jia-Ethan/grok-keysmith Preview-first Grok Build instruction deployment with compat and hook isolation, durable re 508 Codex, OpenCode 1 822 tok
mantisfury/ArkhamMirror Local-first AI-powered document intelligence platform for investigative journalism 502 Claude Code 1 2,199 tok