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

1,345–1,368 of 3,650

trpc-group

trpc-agent-go

★ 1,787

A Go framework for building production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, evaluation, and observability.

SmartFlowAI

EmoLLM

★ 1,784

心理健康大模型 (LLM x Mental Health), Pre & Post-training & Dataset & Evaluation & Depoly & RAG, with InternLM / Qwen / Baichuan / DeepSeek / Mixtral / LLama / GLM series models

Python

delibae

claude-prism

★ 1,782

An offline-first scientific writing workspace powered by Claude. LaTeX + Python + 100+ scientific skills all running locally.

TypeScript

neuml

paperai

★ 1,780

📄 🤖 AI for medical and scientific papers

Python

beam-cloud

beta9

★ 1,778

Ultrafast serverless GPU inference, sandboxes, and background jobs

lmstudio-ai

lmstudio-js

★ 1,776

LM Studio TypeScript SDK

TypeScript

High-Logic

Genie-TTS

★ 1,775

GPT-SoVITS ONNX Inference Engine & Model Converter

Python

julien040

anyquery

★ 1,775

One SQL interface for 60+ tools (e.g., GitHub, Notion, Airtable). Plug into any LLM through MCP.

Mcp-Brasil

mcp-brasil

★ 1,773

MCP Server para 70 APIs públicas brasileiras

Python

standardagents

dmux

★ 1,773

A dev agent multiplexer for git worktrees and coding agents.

HTML

0xSero

turboquant

★ 1,772

TurboQuant: Near-optimal KV cache quantization for LLM inference (3-bit keys, 2-bit values) with Triton kernels + vLLM integration

Python

tile-ai

TileRT

★ 1,771

Tile-Based Runtime for Ultra-Low-Latency LLM Inference

Python

wwbin2017

bailing

★ 1,770

百聆是一个类似GPT-4o的语音对话机器人，通过ASR+LLM+TTS实现，集成DeepSeek R1等优秀大模型，接入openClaw，真正的个人语音助手，时延低至800ms，Mac等低配置也可运行，支持打断

Python

NVIDIA-NeMo

Curator

★ 1,769

Scalable data pre processing and curation toolkit for LLMs

Python

ShenSeanChen

waku-agent

★ 1,769

Waku Waku! Waku Agent is a local-first AI agent harness you actually own, including loop, memory, eval, all in code built to stay legible as it grows.

Python