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

2,857–2,880 of 4,121

maze-agent

Maze

★ 611

A distributed framework for LLM agents

Python

Station-Sciences

bot-crossing

★ 610

A video game for AI agents. Created by Jarren Rocks

JavaScript

benmaster82

Kwipu

★ 609

Ask questions across your Markdown notes using a fully local Graph RAG engine. Built for Obsidian vaults, works with any folder of Markdown files. Extracts entity-relation triples from wikilinks & YAML frontmatter, retrieves answers via hybrid search (vector + BM25 + temporal). Multilingual. No cloud. Runs on Ollama.

Python

berabuddies

Semia

★ 609

Semia, security audit for AI agent skills.

Python

ggozad

haiku.rag

★ 609

Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server

Python

TimeCopilot

timecopilot

★ 609

TimeCopilot: the GenAI Forecasting Agent. Built on LLMs and Time Series Foundation Models, it lets you forecast, cross-validate, and detect anomalies using multiple foundation models through a single API. From finance and energy to web analytics, TimeCopilot turns natural-language queries into production-ready forecasts.

Python

zhudotexe

kani

★ 609

kani (カニ) is a highly hackable microframework for tool-calling language models. (NLP-OSS @ EMNLP 2023)

Python

aryn-ai

sycamore

★ 608

🍁 Sycamore is an LLM-powered search and analytics platform for unstructured data.

Python

FerroxLabs

wayland

★ 608

Wayland - The AI Agent That Perceives. Reasons. Acts. Evolves.

TypeScript

adaline

gateway

★ 607

The only fully local production-grade Super SDK that provides a simple, unified, and powerful interface for calling more than 200+ LLMs.

TypeScript

dbt-labs

dbt-mcp

★ 606

A MCP (Model Context Protocol) server for interacting with dbt.

Python

gethopp

figma-mcp-bridge

★ 606

Figma Plugin & MCP server to bypass API limits

TypeScript

dob323

session-kit

★ 605

Close the terminal windows, not the AI coding sessions. One number takes you back in. Every Claude Code and Codex session in one menu: named, numbered, colour-coded. Open, close, and jump to whichever needs you.

Python

BobMcDear

attorch

★ 604

A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.

Python

chris-koch-penn

gpt3_security_vulnerability_scanner

★ 604

GPT-3 found hundreds of security vulnerabilities in this repo - (this was the first real LLM cybersecurity eval!)

PHP

codejunkie99

fable-orchestrator

★ 604

Fable 5.1 orchestrates. GPT-5.6 Luna and DeepSeek V4 Flash implement.

Shell

craigsc

cmux

★ 604

cmux: tmux for Claude Code

Shell

grishahq

recursive-llm

★ 604

Recursive Language Models for efficient long-context processing. Analyze 1M+ tokens by storing context in a Python REPL while reducing LLM token usage.

Python

matrixorigin

memoria

★ 604

Secure memory management for AI Agents • Ensures data integrity • Reduces hallucinations • Maintains consistent long-term context

Rust

tetherto

qvac

★ 604

Open-source local AI SDK - run AI on-device with no cloud, no API keys. Supports GGUF, RAG, image, music, and video generation, speech-to-text, P2P inference, and more. Cross-platform: Linux, macOS, Windows, Android, iOS.

TypeScript

rajudandigam

agent-inspect

★ 603

Local evidence debugger and trajectory-test toolkit for TypeScript AI agents: inspect causal runs, catch wrong tool paths in CI, and share safe offline evidence.

TypeScript

TexasBedouin

vibe-check

★ 603

By a 12-year product manager who builds 0-to-1: takes a beginner from a vague idea to a buildable plan, then guides the build (GitHub basics, clean-code habits, a verify-and-iterate loop, a checkup for the mess). For Claude Code, Codex, and Antigravity. grill-me is for engineers, vibe-check is for everyone else.

HTML

llm-tools

embedJs

★ 602

A NodeJS RAG framework to easily work with LLMs and embeddings

TypeScript

smallnest

goclaw

★ 602

An open-source AI assistant framework like openclaw