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

3,961–3,984 of 4,156
unconv-ai

Un-0

332

Un-0: an image generator powered by a simulated system of coupled oscillators, an example of an emerging physical computing substrate.

Python
Azure-Samples

SQL-AI-samples

331

Samples using AI and Azure SQL DB

HTML
boringcomputers

nehemiah

331

On-demand Linux computers you can hand to an AI — real Firecracker microVMs with a browser, terminal, coding agents, and an AI that drives them.

TypeScript
elmohq

elmo

331

Open-source Answer Engine Optimization (AEO) and Generative Engine Optimization (GEO) platform. Track how ChatGPT, Claude, Perplexity, Gemini, Copilot, Grok, and Google AI Overviews mention and cite your brand in AI search. MIT-licensed, self-hostable, every metric auditable in code.

TypeScript
Get-Concord-AI

concord-mcp

331

Live messaging for coding agents

TypeScript
MinimalFuture

AgentMesh

331

A Multi-Agent framework that enables AI agents to collaborate effectively, helping you build powerful agent teams for solving complex tasks.

Python
sunriseapps

imagesorcery-mcp

331

An MCP server providing tools for image processing operations

Python
ttguy0707

CyberClaw

331

👾 下一代透明智能体架构 | Next-Gen Transparent Agent Architecture 🔍 全行为审计 | 🛡️ 两段式安全调用 | 🧠 双水位记忆 | ⏰ 心跳任务 📊 P0 级事故率降低 80% | 兼容 OpenClaw + Claude Code 技能生态

Python
hogeheer499-commits

strix-halo-guide

330

Evidence-backed AMD Strix Halo local-AI setup and benchmarks: Qwen3.8, Ollama, llama.cpp, Vulkan/ROCm, large GGUFs, and cross-OEM results.

Python
nghyane

launchdock

330

Use Claude and GPT through one local gateway with OpenAI-compatible and Claude-native APIs.

Go
vakovalskii

NeuralDeskApp

330

Versatile Almost Local, Eventually Reasonable Assistant 🔫

TypeScript
329

D3 charts for React, Angular, Vue, Svelte & Web Components — SVG/Canvas/WebGPU & built-in devtools

TypeScript
corespeed-io

zypher-agent

329

A minimal yet powerful framework for creating AI agents with full control over tools, providers, and execution flow.

TypeScript
mcp-servers-for-revit

mcp-servers-for-revit

329

🔥💧🤖 Sparx fork of the mcp-servers-for-revit/revit-mcp project

C#
329

Obsidian tars plugin that supports text generation based on tag suggestions, using services like DeepSeek, Claude, OpenAI, OpenRouter, SiliconFlow, Gemini, Ollama, Kimi, Doubao, Qwen, Zhipu, QianFan & more.

TypeScript
Ammaar-Alam

minebench

328

Minecraft-style voxel benchmark for comparing AI models (Arena + Sandbox)

TypeScript
AudioLLMs

AudioBench

328

AudioBench: A Universal Benchmark for Audio Large Language Models

Python
InterfaceX-co-jp

genshijin

328

genshijin 原始人 🗿| Claude Code / Codex等AIエージェント 向け超圧縮コミュニケーションスキル。caveman の日本語版をベースに、日本語特有の冗長表現に最適化。

JavaScript
Jeidoban

Ironsmith

328

Create personal Mac apps instantly with a prompt. Supports on-device and cloud LLMs

Swift
kerlos

pordee

328

ตอบสั้นๆ ก็เข้าใจแบบพอดีๆ

JavaScript
aaron-for-value

VeriRun

327

Evidence-first infrastructure for reproducible, isolated executable evaluation and online rewards.

Python
327

Unified LLM API, structured data outputs with LLMs, and agent SDK - in PHP

PHP
FrankChen021

datastoria

327

AI-native ClickHouse console for your cluster diagnostics and query generation, optimization and data visualization.

TypeScript