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

2,233–2,256 of 4,062

yejy53

Editable-Design

★ 903

Agent-driven creation of editable, tastefully crafted visual artifacts.

Python

AQBot-Desktop

AQBot

★ 902

☁️ 轻量级高性能跨平台AI对话 + AI Agent + AI网关桌面客户端 | Lightweight, high-performance cross-platform AI dialogue + AI Agent + AI gateway desktop client

TypeScript

Growth-Kinetics

DiffMem

★ 902

Git Based Memory Storage for Conversational AI Agent

Python

Mininglamp-OSS

octo-cli

★ 902

Metadata-driven CLI for AI Agent Bots — 48 operations across 7 domains, structured JSON envelope I/O, zero interactive prompts.

mosecorg

mosec

★ 902

A high-performance ML model serving framework, offers dynamic batching and CPU/GPU pipelines to fully exploit your compute machine

Python

LeonChaoX

qinyan-academic-skills

★ 901

A curated, multilingual library of 182 installable AI agent skills for end-to-end academic research—spanning literature discovery, scientific writing, grant development, bioinformatics, drug discovery, clinical research, machine learning, and data analysis.

Python

furkankly

zoetrope

★ 900

Watch a Claude Code session as a live flow graph, in your terminal or your browser.

Rust

agentforce314

clawcodex

★ 899

Token efficient Claude Code full Python rebuild. AI Coding Agent in 270K LoC pure Python. Up to 200X Cost Saving!

Python

mlcommons

croissant

★ 899

Croissant is a high-level format for machine learning datasets that brings together four rich layers.

Jupyter Notebook

GewoonJaap

gemini-cli-openai

★ 897

Expose Gemini CLI endpoints as OpenAI API with Cloudflare Workers

TypeScript

kendryte

nncase

★ 897

Open deep learning compiler stack for Kendryte AI accelerators ✨

microsoft

OpenAIWorkshop

★ 896

workshop materials to build intelligent solutions on Open AI

Python

trace-cortex

cortex-app

★ 896

Cortex local-first personal memory app

Python

Shy2593666979

AgentChat

★ 894

AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。

Python