241 ListingsFree scan on submit

Data Science & ML Listings

Compare the best open-source listings for data science & ML. Models, RAG pipelines, embeddings and datasets. Ranked by GitHub stars, with install commands, what each one can touch and scan reports where available.

241 results in Data Science & ML

Active All

Any scan Scanned Gold

Most stars Newest Recently updated

Haiku Rag

Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server

Data Science & ML Scanned 645

Tgo

Open-source AI Agent Customer Service Platform. Build AI agent teams with LLM orchestration, RAG knowledge base, multi-channel support, and human collaboration.

Data Science & ML Not scanned yet 645

XLAM

xLAM: A Family of Large Action Models to Empower AI Agent Systems

Data Science & ML Scanned 641

Rails MCP Server

A Ruby gem implementation of a Model Context Protocol (MCP) server for Rails projects. This server allows LLMs (Large Language Models) to interact with Rails projects through the Model Context Protocol.

Data Science & ML Scanned 575

TravelPlanner

[ICML'24 Spotlight] "TravelPlanner: A Benchmark for Real-World Planning with Language Agents"

Data Science & ML Scanned 566

Opencode Power Pack

55 rigorous skills for Claude Code, Codex, OpenCode 1 and 2, and Pi: code review, security audit, feature development, frontend design, MCP tools, Hugging Face ML/training, and more.

Data Science & ML Scanned 548

AI Interview Codex

Comprehensive ML/AI interview codex with iterative system design, production-ready code, and 2026 standards. Includes LLM/GenAI, RAG systems, agentic AI, and algorithms from scratch.

Data Science & ML Not scanned yet 538

Agent Craft

AI Agent 教学仓库 | 系统化 LangChain、RAG、LangGraph、MCP 全栈实战代码 | 万字博客详解 | 开源可运行示例 | 从零构建智能体

Data Science & ML Scanned 530

Hevy MCP

Manage your Hevy workouts, routines, folders, and exercise templates. Create and update sessions faster, organize plans, and search exercises to build workouts quickly. Stay synced with changes so your training log is always up to date.

Data Science & ML Scanned 529

Structurizr

Structurizr is a "models as code" tool designed for the C4 model.

Data Science & ML Scanned 511

Solon AI

Java AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java26. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.

Data Science & ML Scanned 469

Beever Atlas

Your First LLM-Wiki Conversation Knowledge Base

Data Science & ML Scanned 451

OpenRCA

[ICLR'25] OpenRCA: Can Large Language Models Locate the Root Cause of Software Failures?

Data Science & ML Scanned 448

Nexus

Govern & Secure your AI

Data Science & ML Scanned 436

MCP Local Rag

Local-first RAG server for developers. Semantic + keyword search for code and technical docs. Works with MCP or CLI. Fully private, zero setup.

Data Science & ML Scanned 427

Lc Studylab

LC-StudyLab 是一个完整演示 LangChain v1.0 全家桶能力的开源项目，整合了 LangGraph、DeepAgents、RAG 检索增强生成、Guardrails 安全校验与流式输出智能体等核心特性，帮助开发者系统掌握 LangChain v1 的所有关键组件

Data Science & ML Scanned 406

Nanobanana MCP Server

AI image generation MCP server powered by Google Gemini, with smart model selection and 4K output

Data Science & ML Scanned 402

Context Engine

Context-Engine MCP - Agentic Context Compression Suite

Data Science & ML Scanned 400

Nextcloud MCP Server

Data Science & ML Scanned 400

LangChain ReAct Agent

基于 LangChain/LangGraph 的 ReAct Agent，结合 RAG 检索、工具调用与 Streamlit 界面，面向智能客服与报告生成场景。

Data Science & ML Scanned 399

Computer Use MCP

💻 Give AI models complete control of your computer (probably a bad idea)

Data Science & ML Scanned 391

HiRoute

Make Codex and Claude Code subscriptions go further: a local model router that gives routine agent work to economical models and keeps your strongest model for the hard parts.

Data Science & ML Scanned 367

Deepseek MCP Server

Model Context Protocol server for DeepSeek's advanced language models

Data Science & ML Scanned 362

SourceWeft

Open-source, self-hostable alternative to ChatGPT and NotebookLM — agents, skills, MCP, and cited knowledge in one AI workstation. Your models, your infrastructure. Free to use GPT 6: https://SourceWeft.com/

Data Science & ML Not scanned yet 361

List refreshed November 15, 2026. Data comes from public GitHub repositories.

Data Science & ML ListingsData Science & ML