AI channel
LLM apps

Open-source LLM apps and frameworks

This is the broadest group: chat interfaces, SDKs and frameworks, prompt and evaluation tools, and applications built on large language models. Many work with models from several providers, and some can run models on your own hardware.

How to choose

For anything you plan to ship, check three facts first: the licence, because some popular projects restrict commercial use; whether it supports the model provider you already use; and whether it is still maintained. The At a glance box on every project page answers the licence and maintenance questions from GitHub data.

Most-starred projects

217–240 of 4,628
karpathy

micrograd

★ 17,705

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

Jupyter Notebook
chiphuyen

aie-book

★ 17,658

[WIP] Resources for AI engineers. Also contains supporting materials for the book AI Engineering (Chip Huyen, 2025)

Jupyter Notebook
ahmedkhaleel2004

gitdiagram

★ 17,593

Free, simple, fast interactive diagrams for any GitHub repository

TypeScript
leaningtech

webvm

★ 17,407

Virtual Machine for the Web

JavaScript
hardikpandya

stop-slop

★ 17,354

A skill file for removing AI tells from prose

xx025

carrot

★ 17,201

AI 工具导航大全,帮你快速筛选免费、实用、高效的网站资源

ifixai-ai

iFixAi

★ 17,153

Independent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in the AI Agent Economy. Is the agent doing what is supposed to do? With iFixAi you can have this answer in less than 120 seconds.

Python
★ 17,138

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

Python
kubesphere

kubesphere

★ 17,059

The container platform tailored for Kubernetes multi-cloud, datacenter, and edge management ⎈ 🖥 ☁️

Go
richards199999

Thinking-Claude

★ 17,026

Let your Claude able to think

TypeScript
cft0808

edict

★ 16,915

三省六部制 · OpenClaw Multi-Agent Orchestration System, 9 specialized AI agents with real-time dashboard, model config, and full audit trails.

Python
weaviate

weaviate

★ 16,857

Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database​.

Go
MemoriLabs

Memori

★ 16,779

Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises.

Python

ARIS (Auto-Research-In-Sleep), Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in, works with Claude Code, Codex, OpenClaw, or any LLM agent.

Python
tradecatlabs

vibe-coding-cn

★ 16,680

Vibe Coding 从入门到精通教程|AI 结对编程工作流|Prompt、Skill、Workflow、上下文管理、codex实战指南

Python
citrolabs

ego-lite

★ 16,679

The fastest browser for AI agents to run browser automation, built for sharing your logged-in browser state with your AI agents, like Codex or Claude Code, without disturbing you. Zero cost, zero config.

JavaScript
★ 16,662

"DeepCode: Open Agentic Coding (Agent Harness & Loop Engineering & Multi-Agent Orchestration)"

Python
memvid

memvid

★ 16,566

Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.

Rust
browser-use

web-ui

★ 16,565

🖥️ Run AI Agent in your browser.

Python
★ 16,561

AI 时代的伯克希尔:基于 Claude Code / Codex 的价值投资研究框架。巴菲特·芒格·段永平·李录四大师方法论 + 多Agent并行研究。| AI-era Berkshire: a value investing research framework built for Claude Code / Codex. 4 masters' methodologies + multi-agent adversarial analysis.

Python
googleapis

mcp-toolbox

★ 16,541

MCP Toolbox for Databases is an open source MCP server for databases.

Go
AI4Finance-Foundation

FinRL

★ 16,517

FinRL®: Financial Reinforcement Learning. 🔥

Jupyter Notebook
ai-shifu

ChatALL

★ 16,496

Concurrently chat with ChatGPT, Bing Chat, Bard, Alpaca, Vicuna, Claude, ChatGLM, MOSS, 讯飞星火, 文心一言 and more, discover the best answers

JavaScript
lidge-jun

opencodex

★ 16,448

Universal provider proxy for OpenAI Codex & Claude Code, use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code.

TypeScript