LangChain

AI/ML Tutorial

LangChain

A framework for building applications powered by large language models through composable chains and agents.

LlamaIndex

AI/ML Tutorial

LlamaIndex

A data framework for building LLM applications over custom data with flexible ingestion, indexing, and querying.

Ollama

AI/ML Self-hostable Tutorial

Ollama

Run large language models locally on your own machine with a simple CLI and OpenAI-compatible API.

Open WebUI

AI/ML Self-hostable Tutorial

Open WebUI

A self-hosted ChatGPT-style web interface for running and chatting with local or remote LLMs.

AutoGen

AI/ML Tutorial

AutoGen

Microsoft's framework for building multi-agent AI systems where agents converse with each other to solve tasks.

CrewAI

AI/ML Tutorial

CrewAI

A role-based AI agent framework where you define a crew of agents with specific roles, goals, and tools.

Chroma

Data Self-hostable Tutorial

Chroma

An AI-native open-source vector database for storing and querying embeddings with a simple Python API.

Qdrant

Data Self-hostable Tutorial

Qdrant

A high-performance vector database written in Rust, built for production RAG and similarity search at scale.

Dify

AI/ML Self-hostable Tutorial

Dify

An open-source LLM app development platform with a visual workflow builder, RAG pipeline, and agent tools.

Flowise

AI/ML Self-hostable Tutorial

Flowise

A low-code drag-and-drop UI for building LLM chains and agents, built on top of LangChain.

AnythingLLM

AI/ML Self-hostable Tutorial

AnythingLLM

A private, self-hosted ChatGPT that lets you chat with your own documents using any LLM.

Haystack

AI/ML Tutorial

Haystack

A production-grade NLP framework for building RAG pipelines, question answering, and semantic search systems.

About this repository guide

Search by what you want to build — not by name. GitHub has millions of repositories, but the problem isn't finding one — it's knowing which to use when you have a specific goal. This guide is curated by a developer for developers: each entry explains exactly when to reach for it, so you can pick the right tool without reading five READMEs first.

Currently featuring 20 repositories across AI frameworks, RAG pipelines, vector databases, LLM serving, self-hosted tools, and more. Content starts with AI/ML and grows over time.