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 |
|---|---|---|---|
| nicobailon/pi-mcp-adapter A token-efficient MCP (Model Context Protocol) adapter extension for the Pi coding agent that exposes a single lightweight proxy tool (~200… | 80 | 1606 | active |
| 869413421/ai-moive-studio AICON is a full-stack, self-hostable AI video creation studio that pairs a natural-language-driven agent with an infinite-canvas node edito… | 67 | 1605 | active |
| Rivet A server (with a TypeScript SDK) that runs inside a sandbox and exposes a universal HTTP/SSE API for controlling coding agents like Claude … | 83 | 1604 | active |
| haibbo/cf-openai-azure-proxy A Cloudflare Worker script that proxies OpenAI-compatible API requests to Azure OpenAI Service, letting standard OpenAI clients use Azure d… | 21 | 1604 | active |
| LYiHub/mad-professor-public A desktop AI companion application for reading academic papers, built with PyQt6. It combines PDF parsing and translation, RAG-based retrie… | 24 | 1603 | active |
| spotify/voyager Voyager is an in-memory approximate nearest-neighbor search library implementing the HNSW algorithm, with bindings for Python and Java (and… | 64 | 1602 | stable |
| THUDM/WebGLM WebGLM is an efficient web-enhanced question answering system (KDD 2023) that combines a large language model with web search retrieval and… | 32 | 1602 | active |
| enoch3712/ExtractThinker ExtractThinker is a Python document intelligence library that uses LLMs to extract and classify structured data from documents like PDFs, i… | 71 | 1601 | active |
| xLLM-AI/xllm xLLM is a high-performance C++ inference engine for LLM, VLM, DiT and recommendation models, optimized for heterogeneous AI accelerators su… | 80 | 1600 | active |
| Arboris Novel Arboris-Novel is a self-hosted AI writing companion web application for fiction authors, built in Python and deployable via Docker. It help… | 49 | 1600 | active |
| ponysb/91Writing A browser-based AI novel-writing application built with Vue 3 and Element Plus that integrates user-configured LLM APIs (GPT, Claude, Gemin… | 36 | 1600 | active |
| semperai/amica Amica is an open-source web application for conversing with customizable 3D characters through voice chat, speech recognition, and vision. … | 61 | 1599 | active |
| alibaba/Pai-Megatron-Patch Pai-Megatron-Patch is an open-source deep learning training toolkit from Alibaba Cloud for large-scale training and inference of LLMs and V… | 50 | 1599 | active |
| Ademking/MD-This-Page A browser extension for Chrome and Firefox that converts any webpage into clean, readable Markdown with one click, using Mozilla's Readabil… | 72 | 1598 | active |
| databricks/megablocks MegaBlocks is a lightweight Python library for efficient training of mixture-of-experts (MoE) models, built around its dropless-MoE (dMoE) … | 58 | 1596 | active |
| pytorch/FBGEMM FBGEMM is a collection of highly optimized low-precision matrix multiplication and convolution kernels for server-side deep learning infere… | 91 | 1595 | active |
| MiniMax AI Platform The official MiniMax Model Context Protocol (MCP) server, written in Python, exposing MiniMax's text-to-speech, image generation, and video… | 61 | 1594 | active |
| qnguyen3/chat-with-mlx A chat playground application for running LLMs locally on Apple Silicon Macs using Apple's MLX framework. It provides a chat UI with suppor… | 26 | 1594 | active |
| BAI-LAB/MemoryOS MemoryOS is a Python library that provides an operating-system-inspired memory layer for personalized AI agents, using a hierarchical short… | 59 | 1593 | active |
| NousResearch/autonovel An autonomous AI agent pipeline that writes, revises, evaluates, typesets, illustrates, and narrates a complete novel from a seed concept. … | 44 | 1590 | active |
| amd/gaia GAIA is AMD's open-source Python framework for building AI agents that run entirely locally on AMD Ryzen AI hardware, using NPU and iGPU ac… | 90 | 1587 | active |
| axoviq-ai/synthadoc Synthadoc is an open-source, domain-agnostic LLM knowledge compilation engine that transforms raw documents into structured, human-readable… | 82 | 1587 | active |
| stanfordnlp/pyreft pyreft is Stanford NLP's Python library for Representation Finetuning (ReFT), which adapts frozen language models by learning task-specific… | 52 | 1587 | active |
| cyberark/FuzzyAI FuzzyAI is an automated LLM fuzzing tool from CyberArk that tests LLM APIs for jailbreak vulnerabilities. It ships as a Python CLI with a w… | 48 | 1587 | active |
| D-Star-AI/dsRAG dsRAG is a high-performance retrieval engine for unstructured data, implemented as a Python library for building RAG pipelines. It improves… | 45 | 1586 | active |
| meta-pytorch/torchtune Torchtune is a PyTorch-native library for authoring, post-training, and experimenting with large language models. It provides hackable trai… | 67 | 5819 | maintenance |
| fim-ai/fim-one FIM One is a source-available, self-hostable agent platform that connects enterprise systems (global SaaS plus the China stack like Feishu,… | 60 | 1585 | active |
| RWKV/rwkv.cpp A C++ port of the RWKV language model to the ggml tensor library, providing FP32, FP16, and quantized INT4/INT5/INT8 inference focused on C… | 34 | 1583 | active |
| antvis/AVA AVA is an AI-native visual analytics framework from AntV that lets users load data (CSV, JSON, URL), query it in natural language, and get … | 80 | 1581 | active |
| LangGraph A Python library for building swarm-style multi-agent systems on top of LangGraph, where specialized agents dynamically hand off control to… | 70 | 1580 | active |
| Universal Tool Calling Protocol A TypeScript library that lets AI agents call MCP and UTCP tools by generating and executing code instead of traditional JSON tool-call rou… | 63 | 1579 | active |
| turnstonelabs/turnstone Turnstone is a self-hosted, local-first orchestration platform for tool-using AI agents, letting LLMs use real tools like shell, files, sea… | 78 | 1578 | active |
| patched-codes/patchwork Patchwork is an open-source agentic AI framework and CLI that automates development chores like PR reviews, bug fixing, security patching, … | 68 | 1577 | active |
| Memento-Teams/Memento-Skills Memento-Skills is a generalist, continually-learnable LLM agent framework where reusable skills stored as markdown files serve as persisten… | 71 | 1575 | active |
| shrimbly/node-banana Node Banana is an open-source, node-based visual workflow editor for building AI media generation pipelines. Users connect nodes on an infi… | 81 | 1574 | active |
| hexdocom/lemonai Lemon AI is a full-stack open-source general AI agent platform that runs locally, offering an alternative to Manus and Genspark AI. It comb… | 50 | 1572 | active |
| modelscope/AgentEvolver AgentEvolver is an end-to-end self-evolving training framework for LLM-based agents that unifies automatic task generation (self-questionin… | 47 | 1571 | active |
| MLSysOps/MLE-agent MLE-Agent is an LLM-powered CLI agent that acts as a pairing assistant for machine learning engineers and researchers. It automates ML task… | 53 | 1570 | active |
| egoist/waku Waku is a fast, native desktop application (built in Rust with GPUI) for managing multiple local coding agent CLIs like Claude Code, Codex,… | 79 | 1568 | active |
| cookiy-ai/user-research-skill An open-source AI agent skill (installed as a CLI) that lets AI coding agents like Claude Code, Codex, Cursor, and OpenClaw plan, run, and … | 57 | 1567 | active |
| RunAnywhere RCLI is a single-binary CLI that runs open-source AI models locally on your machine, covering chat, vision, speech-to-text, text-to-speech,… | 82 | 1566 | active |
| unitedbyai/droidclaw DroidClaw is an AI agent that controls Android phones via ADB, using a perceive-reason-act loop over accessibility trees and screenshots to… | 54 | 1566 | active |
| QuantaAlpha/QuantaAlpha QuantaAlpha is an LLM-driven framework for mining quantitative alpha factors using a trajectory-based self-evolving paradigm. Users describ… | 52 | 1563 | active |
| baaivision/Emu3.5 Emu3.5 is BAAI's native multimodal foundation model that jointly predicts next states across vision and language, trained on 10T+ interleav… | 40 | 1561 | active |
| langwatch/better-agents Better Agents is a CLI tool and a set of standards for scaffolding production-ready AI agent projects. It configures coding assistants like… | 65 | 1560 | active |
| Prismer-AI/PrismerCloud Prismer Cloud is a hosted/self-hostable knowledge infrastructure platform for AI agents, providing context fetching and compression, docume… | 68 | 1558 | active |
| neovateai/neovate-code Neovate Code is an open-source AI coding agent that runs in the terminal to generate code, fix bugs, review code, and add tests. It support… | 56 | 1557 | active |
| decoderesearch/SAELens SAELens is a Python library for training sparse autoencoders (SAEs) on language model activations and analyzing them for mechanistic interp… | 90 | 1555 | active |
| openai/openai-java The official Java SDK for accessing the OpenAI REST API, written in Kotlin and published to Maven Central. It provides typed clients for th… | 86 | 1554 | active |
| Bklieger/infinite-bookshelf Infinite Bookshelf is a Streamlit web app that generates entire nonfiction books from a one-line prompt using Llama models on Groq. It scaf… | 32 | 1551 | active |
| RayBytes/ChatMock ChatMock is a Python tool that exposes OpenAI- and Ollama-compatible API endpoints backed by a ChatGPT/Codex account login. It runs a local… | 65 | 1548 | active |
| GitHamza0206/simba Simba is an open-source, production-ready customer service assistant and knowledge management system built around a fully customizable RAG … | 59 | 1546 | active |
| GWUDCAP/cc-sessions cc-sessions is an opinionated installer/extension that sets up a structured, session-based development workflow for Claude Code, including … | 44 | 1546 | active |
| MoonshotAI/Moonlight Moonlight is a 3B/16B Mixture-of-Experts LLM trained with the Muon optimizer, released by Moonshot AI along with a memory- and communicatio… | 33 | 1546 | active |
| RLHFlow/RLHF-Reward-Modeling A collection of training recipes for reward models used in RLHF, covering Bradley-Terry reward models, pairwise preference models, ArmoRM, … | 30 | 1546 | active |
| baichuan-inc/Baichuan-7B Baichuan-7B is an open-source, commercially usable 7-billion-parameter pretrained language model built on the Transformer architecture, tra… | 30 | 5648 | maintenance |
| disler/claude-code-hooks-multi-agent-observability A self-hosted observability system that captures Claude Code hook events via HTTP, stores them in SQLite, and streams them over WebSocket t… | 45 | 1545 | active |
| RTGS2017/NagaAgent NagaAgent is a desktop AI personal assistant framework with an anime (Live2D) virtual character, built in Python with an Electron front end… | 78 | 1542 | active |
| PaperDebugger/paperdebugger PaperDebugger is an AI-powered academic writing assistant delivered as a Chrome extension that integrates directly into Overleaf for in-edi… | 57 | 1542 | active |
| video-db/Director Director is a Python framework for building AI video agents that reason over complex video tasks like search, editing, compilation, and gen… | 38 | 1542 | active |
| SALMONN SALMONN is a family of open-source multi-modal large language models from ByteDance and Tsinghua that unify speech, audio, music, and video… | 70 | 1539 | active |
| KruxAI/ragbuilder RagBuilder is a Python toolkit that automatically builds an optimal, production-ready Retrieval-Augmented Generation (RAG) pipeline for you… | 65 | 1539 | active |
| ATH-MaaS/Marco-o1 Marco-o1 is an open large reasoning model from Alibaba International Digital Commerce, designed for o1-like chain-of-thought reasoning acro… | 58 | 1537 | active |
| ggml-org/llama.vscode A VS Code extension providing local LLM-assisted text and code completion, AI chat, and agentic coding powered by llama.cpp. It supports au… | 84 | 1536 | active |
| tldraw/make-real-starter A starter template for building 'Make Real' style apps that turn hand-drawn UI mockups on a tldraw infinite canvas into working HTML using … | 60 | 1536 | active |
| Mirascope Mirascope is a Python (and TypeScript) library providing a unified, provider-agnostic interface for calling frontier LLMs like OpenAI, Anth… | 91 | 1535 | active |
| Nativ Nativ is a free, MIT-licensed macOS desktop application for running open AI models locally on Apple Silicon Macs, built on MLX-VLM. It prov… | 81 | 1534 | active |
| razzant/ouroboros Ouroboros is an open-source, general-purpose AI agent with persistent identity, durable memory, and the ability to rewrite its own implemen… | 78 | 1533 | active |
| DEEIX-AI/DEEIX-Chat DEEIX Chat is an open-source, self-hostable enterprise AI workspace that unifies access to multiple LLM providers behind one entry point, w… | 80 | 1531 | active |
| techjarves/OpenClaude-Portable A portable AI coding agent that runs Claude Code-style functionality from a USB drive or any folder with no installation, bundling a self-c… | 57 | 1531 | active |
| ibelick/zola Zola is an open-source, self-hostable chat interface for interacting with multiple AI models including OpenAI, Claude, Gemini, Mistral, and… | 42 | 1531 | active |
| borawong/AiMaMi AiMaMi is a native desktop companion app for OpenAI Codex built with Tauri 2, React, and Rust. It consolidates Codex account switching, quo… | 81 | 1529 | active |
| emcf/thepipe thepipe is a Python package and API that extracts clean markdown, multimodal media, and structured data from tricky documents like PDFs, Wo… | 79 | 1529 | active |
| Ch1rpy2613/Mirrai Mirrai is a self-hosted web application that builds AI 'digital twins' of people from uploaded chat logs, photos, and videos, then lets use… | 55 | 1529 | active |
| anaisbetts/mcp-installer An MCP server that installs other MCP servers on your behalf, pulling packages from npm or PyPI. It lets you ask Claude Desktop to install … | 22 | 1529 | active |
| ATH-MaaS/Ovis Ovis is an open-source Multimodal Large Language Model (MLLM) architecture that structurally aligns visual and textual embeddings, with rel… | 62 | 1528 | active |
| akto-api-security/akto Akto is an open-source API and AI security platform that discovers and inventories APIs, AI agents, MCP servers, and LLM usage, then contin… | 94 | 1527 | active |
| import-ai/omnibox OmniBox is a cross-platform, self-hostable AI knowledge hub that lets users collect webpages, files, and voice notes, then parse, index, an… | 89 | 1527 | active |
| bcurts/agentchattr A free, local chat server that lets AI coding agents (Claude Code, Codex, Gemini CLI, and any MCP-compatible agent) and humans coordinate i… | 76 | 1527 | active |
| David-Kunz/gen.nvim A Neovim plugin that generates text using LLMs (primarily via Ollama) with customizable prompts. It streams model responses into editor win… | 33 | 1527 | active |
| kyutai-labs/unmute Unmute is a system that lets any text LLM listen and speak by wrapping it with Kyutai's low-latency speech-to-text and text-to-speech model… | 61 | 1525 | active |
| DocumindHQ/documind Documind is an open-source Node.js library that uses AI/LLMs to extract structured JSON data from PDFs and other documents based on customi… | 30 | 1525 | active |
| workany-ai/workany WorkAny is a cross-platform desktop AI agent application (built with Tauri, React, and Hono) that executes tasks from natural language inst… | 65 | 1524 | active |
| golemcloud/golem Golem is an open-source durable agent runtime and serverless platform for running WebAssembly components in a distributed cloud environment… | 91 | 1522 | active |
| stepfun-ai/Step-Audio2 Step-Audio 2 is an end-to-end multimodal large language model for industry-strength audio understanding and speech conversation, with open-… | 48 | 1521 | active |
| mattzh72/articraft Articraft is a research tool that generates articulated 3D assets from text prompts or reference images by having an LLM write Python using… | 62 | 1519 | active |
| PrathamLearnsToCode/paper2code An agent skill for coding agents like Claude Code that converts an arXiv paper URL into a working Python implementation. It generates citat… | 45 | 1519 | active |
| six2dez/burp-ai-agent Custom AI Agent (formerly Burp AI Agent) is a Burp Suite extension written in Kotlin that integrates LLMs into web security workflows via l… | 77 | 1517 | stable |
| NVlabs/describe-anything Describe Anything Model (DAM) is a vision-language model that generates detailed descriptions of user-specified regions in images and video… | 29 | 1517 | active |
| mattmireles/gemma-tuner-multimodal A Python tool for LoRA fine-tuning of Gemma 4 and 3n models on text, images, and audio using Apple Silicon's Metal Performance Shaders. It … | 60 | 1516 | active |
| memfreeme/memfree MemFree is an open-source hybrid AI search engine that answers questions using both your personal knowledge base and the web, integrating m… | 62 | 1515 | active |
| mbzuai-oryx/Video-ChatGPT Video-ChatGPT is a video conversation model that combines large language models with a pretrained visual encoder adapted for spatiotemporal… | 72 | 1513 | active |
| open-thought/reasoning-gym Reasoning Gym is a Python library of procedural dataset generators and algorithmically verifiable reasoning environments for training LLMs … | 60 | 1512 | active |
| andrewnguonly/Lumos Lumos is a Chrome extension that acts as a RAG-powered LLM co-pilot for browsing the web, letting users summarize pages and ask questions a… | 18 | 1511 | active |
| microsoft/ai-dev-gallery AI Dev Gallery is a Windows application from Microsoft that lets developers explore over 25 interactive samples powered by local AI models … | 67 | 1510 | active |
| NPC-Worldwide/npcpy npcpy is a Python library providing primitives for building applications with multimodal LLMs, agentic AI, and knowledge graphs. It support… | 84 | 1509 | active |
| ovg-project/kvcached kvcached is a Python library that brings OS-style virtual memory abstraction to KV cache management for LLM serving and training on shared … | 72 | 1509 | active |
| Open-Source-Legal/OpenContracts OpenContracts is a self-hosted, MIT-licensed document intelligence platform that turns document repositories into a programmable citation g… | 89 | 1508 | active |
| jgravelle/AutoGroq AutoGroq is a Python application that dynamically generates tailored teams of AI agents for Autogen and similar frameworks based on user pr… | 16 | 1508 | active |
| imoneoi/openchat OpenChat is a library of open-source large language models fine-tuned with C-RLFT, an offline reinforcement learning strategy that learns f… | 20 | 5485 | maintenance |