llm

Empower Large Language Models (LLM) using Knowledge Graph based Retrieval-Augmented Generation (KG-RAG) for knowledge intensive tasks

Flow-Like: Strongly Typed Enterprise Scale Workflows. Built for scalability, speed, seamless AI integration and rich customization.

ELI5 — A Claude Code skill that explains anything to anyone: kids, managers, engineers, parents. Adapts tone, vocabulary, and analogies to match the audience.

A LLM semantic caching system aiming to enhance user experience by reducing response time via cached query-result pairs.

⛓️ Serving LangChain LLM apps and agents automagically with FastApi. LLMops

Pure Rust implementation of a minimal Generative Pretrained Transformer

MAC (Multi-Agent CAD): A decoupled multi-agent framework for text-to-CAD generation via constrained test-time compute

“AI-Compass”将为社区指引在 AI 技术海洋中航行的方向，无论你是初学者还是进阶开发者，都能在这里找到通往 AI 各大方向的路径。旨在帮助开发者系统性地了解 AI 的核心概念、主流技术、前沿趋势，并通过实践掌握从理论到落地的全过程。

Open-source, self-hosted AI app builder — an agent builds real apps in isolated sandboxes on your own server, each live at a preview URL. Self-host in one command. MIT.

Large Language Models (LLMs) tutorials & sample scripts, ft. langchain, openai, llamaindex, gpt, chromadb & pinecone

The Typescript MCP Framework

AI Pair Programming in Emacs with Aider

Chat with AI over SSH.

Code research platform for AI agents; find, understand, and prove context across your code and all of GitHub, in a fraction of the tokens. One toolset, MCP or CLI

AgentKit: Build multi-agent networks in TypeScript with deterministic routing and rich tooling via MCP.

List of awesome hosting sorted by minimal plan price

All-in-one native macOS AI chat application for virtually any AI provider

Whale — blazingly fast, terminal-first AI coding agent for DeepSeek. ~98% prompt cache hit rate, 1M context, MCP tools, dynamic workflows.

Pure C++ implementation of several models for real-time chatting on your computer (CPU & GPU)

🚀 Self-hosted AI automation platform. Deploy n8n, Ollama, Flowise, RAG, Supabase & 30+ tools with one command. Auto HTTPS. Free Zapier/Make alternative.

MindSpore + 🤗Huggingface: Run any Transformers/Diffusers model on MindSpore with seamless compatibility and acceleration.

Read it. See it. Get it. Built at GDG AI Hack Milan 2026 for "Learn Different" track.

[ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.

Local-first, open-source AI assistant for your data. Unify tasks, notes, docs, photos, and bookmarks. Private, self-hosted, and extensible via APIs.

Sudoless Apple Silicon system monitor (native SwiftUI GUI) with ANE / Media Engine / memory-bandwidth tracking

Open-source desktop AI agent workspace with one-click Claude Code, Codex, OpenClaw, Hermes Agent setup and custom LLM model routing.

Mock everything your AI app talks to — LLM APIs, MCP, A2A, AG-UI, vector DBs, search. One package, one port, zero dependencies.

Lumina Note - A modern Markdown note-taking app with live preview, bidirectional links, and AI assistant

Deep research agent to help you find the best GitHub repositories 🕵️!

A highly optimized LLM inference acceleration engine for Llama and its variants.