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

1–24 of 4,584

affaan-m

ECC

★ 269,495

ECC supplies agent skills, security checks, memory patterns, and research workflows aimed at reducing wasted context during coding sessions.

JavaScript

NousResearch

hermes-agent

★ 249,187

Hermes Agent runs as a personal agent with persistent memory, scheduled work, tool use, and integrations for messaging and local services.

Python

Significant-Gravitas

AutoGPT

★ 187,586

Open-source platform for building and running AI agents that complete full workflows, defined in plain English or a visual builder and run on demand or on a schedule.

Python

firecrawl

★ 186,493

The API to search, scrape, and interact with the web at scale. 🔥

TypeScript

ollama

★ 181,861

Run leading open models locally with a simple developer experience.

anthropics

skills

★ 178,978

Anthropic's public collection of Agent Skills — folders of instructions, scripts, and resources Claude loads dynamically to perform specialized tasks repeatably.

Python

huggingface

transformers

★ 166,652

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Python

langgenius

dify

★ 157,512

Dify is an open-source LLM app platform combining agentic workflows, RAG pipelines and model management, deployable on cloud, VPC, or self-hosted infrastructure.

TypeScript

open-webui

★ 153,167

Open WebUI is a self-hosted AI interface that runs entirely offline, supporting Ollama and OpenAI-compatible APIs with a built-in inference engine for RAG.

Python

anthropics

claude-code

★ 148,319

Claude Code is an agentic coding tool that lives in your terminal, executing routine tasks, explaining complex code, and handling git workflows via natural language.

Python

DietrichGebert

ponytail

★ 147,444

Ponytail adds YAGNI-focused review instructions that push coding agents to remove unnecessary abstractions and avoid speculative code.

JavaScript

langchain-ai

langchain

★ 147,049

LangChain gives agent builders a common layer for models, tools, retrieval, and multi-step execution.

Python

ggml-org

llama.cpp

★ 129,881

llama.cpp runs LLM inference in plain C/C++, serving models locally through a REST API and web UI with multimodal support in its llama-server.

C++

harry0703

MoneyPrinterTurbo

★ 126,642

MoneyPrinterTurbo uses language models and an automated media pipeline to create short videos from a topic or keyword.

Python

Graphify-Labs

graphify

★ 122,380

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.

Python

TauricResearch

TradingAgents

★ 108,599

TradingAgents coordinates specialized language-model agents for market research, debate, risk review, and simulated trading decisions.

Python

JuliusBrussee

caveman

★ 108,342

Caveman rewrites verbose command output into a compact format so Claude Code can spend fewer tokens on routine tool results.

JavaScript

pytorch

★ 103,522

PyTorch is a Python package for GPU-accelerated tensor computation and deep neural networks built on a tape-based autograd system, extensible via NumPy and SciPy.

Python

vllm-project

vllm

★ 92,677

A high-throughput and memory-efficient inference and serving engine for LLMs.

Python

modelcontextprotocol

servers

★ 90,676

Collection of reference MCP server implementations maintained by the steering group, meant as educational examples for developers building their own MCP servers.

TypeScript

OpenHands

★ 89,526

OpenHands is a self-hosted control center for coding agents, running Claude Code, Codex, or any ACP-compatible agent across local, remote, and cloud backends.

Python

bytedance

deer-flow

★ 83,220

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

Python

lobehub

★ 82,903

LobeHub acts as a Chief Agent Operator that organizes your AI agents into round-the-clock operations, handling hiring, scheduling, and reporting while you stay in charge.

TypeScript

rtk-ai

rtk

★ 81,911

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies.

Rust