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

3,361–3,384 of 4,152
angelnicolasc

graymatter

471

30 sec to give your AI agents persistent memory. Reduce 90% token consumption while also maintaining quality.

Go
cosmicstack-labs

mercury-agent-skills

471

A curated registry of reusable Mercury Agent, Open Claw or Hermes Agent skills designed for real developer workflows, persistent memory, and token-efficient execution.

JavaScript
jatinkrmalik

LLMFeeder

471

Browser extension to convert web pages to clean Markdown and copy to clipboard so you can feed it to your favorite LLM model as context with just 1 click!

JavaScript
Miasyster

QuantGPT

471

Agent-driven alpha factory — LLM autonomously designs, backtests, and submits factors to WorldQuant BRAIN

Python
NPC-Worldwide

incognide

471

Explore the unknown, build the future, own your data.

TypeScript
471

A multithreaded 🕸️ web crawler that recursively crawls a website and creates a 🔽 markdown file for each page, designed for LLM RAG

Python
razzant

claudexor

471

Multi-harness control plane for Claude Code, Codex, Cursor, and OpenCode: quota-aware rotation across multiple Claude/Codex subscriptions, shared thread context, and cross-model review.

TypeScript
RickyTong1

audit-harness

471

Three-layer audit enforcement framework for AI agents — hooks, skills, context recovery, and audit-driven daily reports

Shell
AgentFlocks

flocks

470

Flocks is an agentic SecOps platform.

Python
AgentSkillOS

SkillAnything

470

Making ANY Software Skill-Native -- Auto-generate production-ready AI Agent Skills for Claude Code, OpenClaw, Codex, and more.

Python
GalaxyGeneralRobotics

Humanoid-GPT

470

Official implementation of AstraBrain-WBC 0.5

Python
morapelker

hive

470

Project/Worktree manager, deeply integrated with AI agents to increase productivity and multitask efficiently

TypeScript
renee-jia

scholar-loop

470

An autonomous AI scientist: a multi-agent loop over literature, experiments, self-critique and write-up, with deterministic guards against reward-hacking and hallucination.

Python
CristianOlivera1

Aura

469

Ambient UI gradients built with layered CSS blend modes. Backgrounds that feel like light.

TypeScript
VisActor

VMind

469

Not only automatic, but also intelligent. An Intelligent data Visualization System, based on LLM.

TypeScript
yaojingang

GEORank

469

Open-source GEO ranking and generative engine optimization platform.

Python
468

面向 Windows 的 ChatGPT 账号注册、邮箱 OTP、账号管理与支付工作台

Python
barry-ran

QuickDesk

468

QuickDesk is the first AI-native remote desktop — an open-source, free application with a built-in MCP (Model Context Protocol) Server that lets any AI agent see and control remote computers.

QML
lablup

mlxcel

468

High-performance LLM, VLM, embedding, reranking, and audio inference for Apple Silicon and NVIDIA CUDA systems.

Rust
SuperJJ007

CSSwitch

468

帮你的 Claude Science 一键接入你自己的 API:DeepSeek / 通义千问 / 智谱 GLM / Kimi / MiniMax / 小米 MiMo / 硅基流动 / OpenRouter / 任意 OpenAI·Anthropic 兼容端点

Rust
vllm-project

vime

468

An LLM post-training framework with vLLM for RL Scaling

Python
alantech

marsha

467

Marsha is a functional, higher-level, English-based programming language that gets compiled into tested Python software by an LLM

Python

给 Codex Desktop 一键换肤:OpenAI Codex/ChatGPT 桌面端主题工具,CDP 注入零修改应用,Miku/原神/鸣潮/火影/恋与深空 9 预设+自定义图片取色 | One-click theme & skin switcher for OpenAI Codex Desktop (macOS/Windows)

JavaScript
467

🪢 Langfuse Python SDK - Instrument your LLM app with decorators or low-level SDK and get detailed tracing/observability. Works with any LLM or framework

Python