Open-source large-language-models software
3737 open-source libraries, tools and applications tagged large-language-models, ranked by how closely large-language-models is their primary purpose, then by adoption and maintenance health. Each entry links to a page with sources, use cases and when to choose or avoid it.
3737 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| Xchat1/cursor2api-go A Go service that converts Cursor's web interface into an OpenAI chat/completions-compatible API, exposing models like gemini-3-flash with … | 48 | 1056 | maintenance |
| tibbar213/team-manage A self-hosted FastAPI application for managing ChatGPT Team accounts, letting admins bulk-import Team accounts and generate redemption code… | 49 | 1054 | maintenance |
| mpaepper/llm_agents A small Python library for building agents controlled by large language models, inspired by LangChain but implemented from scratch in very … | 40 | 1054 | maintenance |
| huggingface/optimum-quanto Optimum Quanto is a PyTorch quantization backend for Hugging Face Optimum that quantizes model weights (int2/int4/int8/float8) and activati… | 66 | 1053 | maintenance |
| jondurbin/airoboros Airoboros is a Python library implementing a heavily modified version of the Self-Instruct paper to generate high-quality synthetic instruc… | 21 | 1053 | maintenance |
| CSHaitao/LexiLaw LexiLaw is a fine-tuned Chinese legal large language model based on ChatGLM-6B, providing legal consultation and Q&A capabilities. It inclu… | 58 | 1046 | maintenance |
| Xwin-LM/Xwin-LM Xwin-LM is an open-source project for LLM alignment technologies including supervised fine-tuning, reward models, reject sampling, and RLHF… | 28 | 1037 | maintenance |
| dandelionsllm/pandallm Panda is an open-source project for overseas Chinese large language models, providing PandaLLM model weights (continued pretraining of LLaM… | 30 | 1027 | maintenance |
| microsoft/Llama-2-Onnx Microsoft's optimized ONNX export of Meta's Llama 2 models (7B and 13B, pretrained and fine-tuned, float16/float32), distributed via Git su… | 29 | 1025 | maintenance |
| CaviraOSS/OpenMemory OpenMemory is a local-first, self-hosted cognitive memory engine that gives LLM applications and AI agents persistent long-term memory, wit… | 66 | 4523 | experimental |
| turtlesoupy/this-word-does-not-exist A project that trains a GPT-2 variant to invent fake English words with generated definitions and example sentences, powering the thiswordd… | 68 | 1024 | maintenance |
| zabirauf/AutoGPT.js AutoGPT.js is an open-source web application that runs AutoGPT-style autonomous GPT agents directly in the browser. It supports file creati… | 31 | 1024 | maintenance |
| i-am-bee/acp The Agent Communication Protocol (ACP) is an open protocol with Python and TypeScript SDKs for enabling AI agents built on different framew… | 10 | 1019 | maintenance |
| zahidkhawaja/langchain-chat-nextjs A Next.js frontend for the LangChain Chat chatbot, which answers questions about LangChain documentation with cited sources. It provides th… | 22 | 1015 | maintenance |
| kakaobrain/kogpt KakaoBrain's KoGPT, a Korean Generative Pre-trained Transformer (GPT) model with 6B parameters, distributed via Hugging Face with inference… | 23 | 1011 | maintenance |
| cbh123/narrator A Python app that watches your webcam and generates David Attenborough-style narration of what it sees, using GPT vision models and ElevenL… | 66 | 4428 | experimental |
| varunshenoy/GraphGPT GraphGPT is a web application that converts unstructured natural language text into a knowledge graph using GPT-3, visualizing entities and… | 32 | 4423 | experimental |
| aws-samples/bedrock-access-gateway A proxy service that exposes Amazon Bedrock foundation models through OpenAI-compatible RESTful APIs, letting existing OpenAI SDK-based app… | 10 | 1004 | maintenance |
| fcakyon/autollm AutoLLM is a Python library for rapidly building RAG-based LLM web apps and APIs, offering a unified API over 100+ LLM providers and 20+ ve… | 10 | 1003 | maintenance |
| susiai/susi_device SUSI Device provides sources to install the SUSI AI assistant stack on a Raspberry Pi, combining microphone/speaker, a small display, a loc… | 32 | 1000 | maintenance |
| aiwaves-cn/RecurrentGPT RecurrentGPT is a Python implementation of a paper-proposed framework that simulates LSTM-style recurrence using natural language and promp… | 30 | 999 | maintenance |
| vijaythecoder/awesome-claude-agents A curated collection of 24 specialized Claude Code subagent definitions that form an orchestrated AI development team. Agents are installed… | 28 | 4388 | experimental |
| build-with-groq/g1 g1 is a Python prototype that uses prompting strategies with Llama-3.1 70b on Groq to produce o1-like visible reasoning chains for solving … | 46 | 4162 | experimental |
| lencx/nofwl NoFWL is a cross-platform desktop application for accessing ChatGPT, built with Tauri and Rust. It wraps the ChatGPT experience in a native… | 22 | 4127 | experimental |
| apple/ml-mgie MGIE (MLLM-Guided Image Editing) is Apple's research implementation of instruction-based image editing guided by multimodal large language … | 69 | 3872 | experimental |
| Significant-Gravitas/Auto-GPT-Plugins A collection of official and community plugins for Auto-GPT, the autonomous AI agent framework, providing additional capabilities like web … | 10 | 3821 | experimental |
| llSourcell/Doctor-Dignity Doctor Dignity is a fine-tuned Llama2 7B model that can pass the US Medical Licensing Exam, built with PyTorch, Transformers, TRL, and ONNX… | 29 | 3809 | experimental |
| 0hq/WebGPT WebGPT is a vanilla JavaScript and HTML implementation of GPT transformer inference running in the browser via WebGPU, in under ~1500 lines… | 30 | 3787 | experimental |
| axtonliu/axton-obsidian-visual-skills A pack of prompt-based skills for Claude Code that generates Obsidian Canvas, Excalidraw, and Mermaid diagrams from text descriptions. It s… | 62 | 3639 | experimental |
| TinyAGI/tinyagi TinyAGI is a self-hosted multi-agent orchestrator that runs teams of AI agents collaborating across isolated workspaces, reachable via Disc… | 57 | 3619 | experimental |
| b-nnett/grok-bot-0.18-reconstructed An unofficial, source-oriented reconstruction of the Grok Bot 0.18.0 macOS Electron app, with readable TypeScript implementations of its ru… | 10 | 3521 | experimental |
| MoonshotAI/Attention-Residuals Official implementation of Attention Residuals (AttnRes), a drop-in replacement for standard residual connections in Transformers that lets… | 44 | 3516 | experimental |
| corbt/agent.exe Agent.exe is a simple Electron app that lets Anthropic's Claude 3.5 Sonnet computer-use capabilities take control of your local computer to… | 23 | 3476 | experimental |
| googleanalytics/google-analytics-mcp A local MCP (Model Context Protocol) server that exposes Google Analytics Admin and Data APIs as tools for LLMs like Gemini. It lets AI ass… | 81 | 3464 | experimental |
| xjdr-alt/entropix Entropix is a research project implementing entropy-based sampling and parallel chain-of-thought decoding for large language models, aiming… | 23 | 3430 | experimental |
| NVIDIA-NeMo/Switchyard Switchyard is a Rust proxy and library that routes LLM traffic across models and providers while translating between OpenAI Chat, Anthropic… | 77 | 3421 | experimental |
| DevAgentForge/Open-Claude-Cowork Open Claude Cowork (Agent Cowork) is an open-source desktop AI assistant that serves as a GUI alternative to Claude Cowork, helping users w… | 54 | 3393 | experimental |
| codeaashu/claude-code A repository containing the leaked TypeScript source code of Anthropic's Claude Code, an agentic coding CLI that edits files, runs commands… | 56 | 3372 | experimental |
| danielgross/localpilot A local proxy server that emulates GitHub Copilot by running open-source code-completion LLMs (via llama.cpp/GGML) on a Mac, so VS Code's C… | 28 | 3337 | experimental |
| oboard/claude-code-rev A restored, runnable source tree of Anthropic's Claude Code CLI, reconstructed from source maps with shims filling unrecoverable modules. I… | 55 | 3300 | experimental |
| microsoft/amplifier Amplifier is a modular, extensible AI-powered development assistant delivered as a command-line tool from Microsoft. It provides chat and a… | 63 | 3126 | experimental |
| evilsocket/cake Cake is a multimodal AI inference server written in Rust that runs text, image, and voice models on a single device or shards them across a… | 56 | 3126 | experimental |
| daveshap/OpenAI_Agent_Swarm A framework for building a Hierarchical Autonomous Agent Swarm (HAAS) on top of OpenAI's agent APIs, where a core set of governed agents ca… | 10 | 3097 | experimental |
| snyk/agent-scan Snyk Agent Scan is a Python-based CLI security scanner that discovers installed AI agent components (agent harnesses, MCP servers, and agen… | 81 | 3095 | experimental |
| cheshire-cat-ai/core Cheshire Cat AI is a Python framework and microservice for building conversational AI agents with LLMs, tools, RAG, and plugins, served wit… | 87 | 3093 | experimental |
| collabs-inc/collab-public Collaborator is a native desktop application (Electron-based) that provides an infinite-canvas environment for working with AI coding agent… | 71 | 3074 | experimental |
| danielgross/whatsapp-gpt A Go application that bridges WhatsApp messages to ChatGPT by running a WhatsApp client and a browser session controlling ChatGPT. It also … | 32 | 3055 | experimental |
| OpenNSWM-Lab/FAROS FAROS is a blueprint-driven AutoResearch runtime that orchestrates end-to-end AI research workflows, from idea generation through experimen… | 56 | 3037 | experimental |
| pingcap/autoflow AutoFlow is an open-source Graph RAG knowledge base tool that builds knowledge graphs over crawled documentation and answers questions via … | 60 | 2974 | experimental |
| RootbeerComputer/backend-GPT An experimental project that replaces a traditional backend and database with an LLM. Users describe their app's purpose, provide an initia… | 32 | 2931 | experimental |
| yakami129/VirtualWife VirtualWife is a self-hosted virtual digital human (AI companion) application that combines VRM 3D character models with LLM-powered conver… | 21 | 2907 | experimental |
| Everlyn-Labs/Everlyn-1 Everlyn-1 is an open autoregressive foundational video AI model from Everlyn Labs, accompanied by research on video compression/tokenizatio… | 67 | 2893 | experimental |
| Einsia/OpenChronicle OpenChronicle is a local-first, open-source memory layer for tool-capable LLM agents, running on macOS. It captures structured context from… | 48 | 2815 | experimental |
| CompozyOS CompozyOS is a self-hosted 'operating system for AI agents' written in Go that wraps existing agent CLIs (Claude Code, Codex, Gemini CLI, O… | 78 | 2810 | experimental |
| wquguru/nof0 NOF0 is an open-source AI trading arena that lets multiple LLM/agent-driven strategies compete in live cryptocurrency markets, each startin… | 39 | 2749 | experimental |
| gvzdv/claudish-to-english A Claude Code plugin that rewrites assistant messages into plain English using a local LLM via ollama, or alternatively the codex CLI, Anth… | 77 | 2728 | experimental |
| openai/weak-to-strong OpenAI's research codebase implementing weak-to-strong generalization experiments from their alignment paper, where a strong pretrained mod… | 10 | 2548 | experimental |
| mshumer/gpt-author A Jupyter notebook-based tool that chains GPT-4/Claude 3 and Stable Diffusion API calls to generate complete fantasy novels from a user pro… | 30 | 2530 | experimental |
| Bitterbot-AI/bitterbot-desktop Bitterbot is a local-first desktop AI agent with persistent memory, a 'dream engine' that consolidates skills while idle, and a peer-to-pee… | 83 | 2478 | experimental |
| semanser/codel Codel is a self-hosted, fully autonomous AI agent that executes complex tasks using a sandboxed Docker environment with terminal, browser, … | 16 | 2476 | experimental |
| paulpierre/RasaGPT RasaGPT is a headless LLM chatbot platform built on top of Rasa and Langchain, serving as a boilerplate and reference implementation. It in… | 50 | 2466 | experimental |
| shepherd-agents/shepherd Shepherd is a Python runtime substrate that records LLM agent executions as reversible, Git-like traces so meta-agents can inspect, fork, r… | 76 | 2464 | experimental |
| IlyaRice/RAG-Challenge-2 A Python implementation of the winning RAG system from the Enterprise RAG Challenge 2 competition, answering questions about company annual… | 26 | 2458 | experimental |
| jennyzzt/dgm Darwin Gödel Machine (DGM) is a research implementation of a self-improving AI agent that iteratively rewrites its own codebase and validat… | 32 | 2424 | experimental |
| keijiro/AIShader A Unity editor plugin that generates shaders from prompts using the ChatGPT API. It is a proof-of-concept tool demonstrating LLM-driven sha… | 31 | 2381 | experimental |
| facebookresearch/large_concept_model Official PyTorch implementation of Meta's Large Concept Models (LCM), which perform language modeling by autoregressively predicting senten… | 22 | 2381 | experimental |
| Autodoc Autodoc is an experimental CLI toolkit that auto-generates documentation for git repositories using large language models like GPT-4. It in… | 31 | 2373 | experimental |
| dot-agent/nextpy Nextpy is a pure-Python fullstack web framework optimized for AI agents and code generation, describing itself as a self-modifying software… | 19 | 2347 | experimental |
| dvmazur/mixtral-offloading A Python library enabling efficient inference of Mixtral-8x7B mixture-of-experts language models on limited hardware like Google Colab or c… | 27 | 2334 | experimental |
| tanbiralam/claude-code A repository containing the leaked TypeScript source of Anthropic's Claude Code, an agentic coding CLI that runs in the terminal and perfor… | 47 | 2288 | experimental |
| mshumer/gpt-investor An experimental AI agent notebook that uses Claude 3 models to analyze stocks in a given industry, gathering financial data, news, and anal… | 26 | 2264 | experimental |
| Sumandora/remove-refusals-with-transformers A proof-of-concept Python script that removes refusal behavior from LLMs by ablating the refusal direction using pure Hugging Face Transfor… | 46 | 2230 | experimental |
| Future AGI Future AGI is an open-source, self-hostable platform for evaluating, observing, and improving LLM and AI agent applications, combining trac… | 77 | 2146 | experimental |
| emcf/engshell Engshell is an English-language shell powered by LLMs that translates natural-language commands into executable Python code on any OS. It i… | 57 | 2145 | experimental |
| YiVal/YiVal YiVal is an open-source Python framework that automatically tunes prompts, RAG configurations, and model parameters for generative AI appli… | 20 | 2137 | experimental |
| renatoasse/opensquad opensquad is a multi-agent orchestration framework that lets users describe tasks in natural language and automatically assembles teams of … | 46 | 2120 | experimental |
| Emanuele-web04/synara Synara is a local-first desktop application that serves as a workspace and control plane for coding-agent runtimes like Claude Code, Codex,… | 78 | 2106 | experimental |
| Zep Graphiti is an open‑source framework for building and querying temporal knowledge graphs that evolve with each interaction. It powers Zep's… | 93 | 210 | active |
| fikrikarim/parlor Parlor is a fully on-device, real-time multimodal voice assistant similar to GPT-Live, combining speech recognition, a Gemma vision-languag… | 73 | 2076 | experimental |
| microsoft/aici AICI (Artificial Intelligence Controller Interface) is a Microsoft Research prototype that lets developers write Wasm-based controllers to … | 19 | 2076 | experimental |
| Hyperspace Hyperspace AGI is an experimental peer-to-peer network where autonomous AI agents collaboratively train language models and share research … | 82 | 2072 | experimental |
| fiatrete/OpenDAN-Personal-AI-OS OpenDAN is an open-source Personal AI Operating System that consolidates various AI modules into one platform for personal use. It lets use… | 50 | 2061 | experimental |
| virattt/ai-financial-agent An AI-powered financial research agent built in TypeScript that answers investment research questions via a chat interface, using generativ… | 35 | 2033 | experimental |
| Ante Ante is a self-contained terminal-based coding agent harness written in Rust, distributed as a single ~15MB binary with zero runtime depend… | 80 | 2011 | experimental |
| browser-use/macOS-use A Python library that lets LLM-powered AI agents control and interact with any macOS application via the accessibility layer, from the make… | 10 | 2002 | experimental |
| WeaveMindAI/weft Weft is a programming language (currently a POC) where LLMs, humans, APIs, and infrastructure are first-class primitives for building AI or… | 67 | 1989 | experimental |
| team9ai/team9 Team9 is a collaborative workspace application where AI agents live alongside human teammates in channels, threads, and shared docs, built … | 71 | 1979 | experimental |
| happier-dev/happier Happier is an open-source, end-to-end encrypted companion client for AI coding agents like Claude Code, Codex, Gemini, and OpenCode. It let… | 83 | 1968 | experimental |
| Mini-Omni Mini-Omni is an open-source multimodal large language model that performs real-time end-to-end speech-to-speech conversation with streaming… | 23 | 1935 | experimental |
| Elysia Elysia is an agentic platform and Python package from Weaviate where a decision agent dynamically chooses tools arranged in a decision tree… | 51 | 1919 | experimental |
| Continual-Intelligence/SEAL SEAL (Self-Adapting LLMs) is a research framework from MIT CSAIL that trains language models via reinforcement learning to generate their o… | 31 | 1870 | experimental |
| StartupHakk/OpenMonoAgent.ai OpenMonoAgent is a terminal-native coding agent that runs entirely on local hardware, pairing a .NET 10 CLI with a bundled llama.cpp infere… | 57 | 1866 | experimental |
| Standard-Intelligence/hertz-dev Hertz-dev is an open-source 8.5B parameter autoregressive base model for full-duplex conversational audio, released by Standard Intelligenc… | 22 | 1799 | experimental |
| flutter/genui A Flutter SDK for building interactive generative UI, where LLMs and agents compose dynamic graphical interfaces at runtime from a JSON-bas… | 81 | 1782 | experimental |
| zhnt/loushang Loushang is an AI-native agent harness for coding workflows, delivered as a Python CLI and terminal workbench (`loushang code`) with multi-… | 59 | 1758 | experimental |
| lidangzzz/goal-driven Goal-Driven is a prompt-based multi-agent methodology that wraps coding agents like Claude Code or Codex in a master-agent loop, keeping su… | 44 | 1744 | experimental |
| cfortuner/promptable Promptable is a TypeScript/JavaScript library for building LLM-powered applications, providing prompt templating, model providers (OpenAI, … | 10 | 1744 | experimental |
| richardyc/Chrome-GPT Chrome-GPT is an experimental AutoGPT agent that uses LangChain and Selenium to control a full Chrome browser session on your desktop. It c… | 30 | 1743 | experimental |
| Klotzkette/claude-fuer-deutsches-recht An experimental collection of Claude skills, sub-agents, and workflows adapted for German legal practice, covering areas like employment, c… | 78 | 1741 | experimental |
| Cormanz/smartgpt SmartGPT is an experimental Rust program that lets LLMs like GPT-3.5 and GPT-4 autonomously complete complex tasks by breaking them into su… | 31 | 1737 | experimental |