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 |
|---|---|---|---|
| CreminiAI/skillpack SkillPack is an open-source CLI and runtime for packaging AI skills (prompts, scripts, tools) into distributable zip bundles that run as lo… | 58 | 1203 | active |
| openvinotoolkit/nncf NNCF is Intel's Neural Network Compression Framework, a Python library providing post-training and training-time compression algorithms (qu… | 92 | 1202 | active |
| heyhuynhgiabuu/proxypal ProxyPal is a native desktop app (Tauri-based) that wraps CLIProxyAPI to expose AI subscriptions like Claude, ChatGPT, Gemini, and GitHub C… | 76 | 1202 | active |
| Cerebras/modelzoo Cerebras Model Zoo is a collection of reference deep learning model implementations (Llama, Mixtral, DINOv2, Llava, etc.) with configs and … | 74 | 1202 | active |
| FranciscoMoretti/chat-js ChatJS is an open-source, production-ready AI chat application built with Next.js and TypeScript, offering authentication, 120+ models via … | 85 | 1200 | active |
| JackHopkins/factorio-learning-environment An open-source framework for developing and evaluating LLM agents in the game of Factorio, providing an open-ended, non-saturating benchmar… | 83 | 1199 | active |
| deepseek-ai/DeepSeek-VL DeepSeek-VL is an open-source vision-language foundation model for real-world multimodal understanding, released with model weights and inf… | 26 | 4183 | maintenance |
| TrafficGuard/typedai TypedAI is a TypeScript-first platform for building and running autonomous AI agents, LLM workflows, chatbots, and AI software engineering … | 50 | 1197 | active |
| huggingface/Math-Verify A Python library from Hugging Face for robustly parsing and verifying mathematical expressions, designed to evaluate Large Language Model o… | 47 | 1197 | active |
| zai-org/CogAgent CogAgent is an open-source vision-language model (VLM) based GUI agent that understands screen captures and natural language to automate in… | 30 | 1197 | active |
| sozercan/kubectl-ai A kubectl plugin written in Go that generates and applies Kubernetes manifests from natural-language prompts using OpenAI GPT or OpenAI API… | 21 | 1196 | active |
| Zen4-bit/Proxima Proxima is a local-first Electron application that runs a multi-AI Model Context Protocol (MCP) server, routing ChatGPT, Claude, Gemini, an… | 69 | 1195 | active |
| NVIDIA/audio-flamingo NVIDIA's PyTorch implementation of the Audio Flamingo series of large audio-language models (AF1, AF2, AF3, and Music Flamingo) for audio u… | 47 | 1195 | active |
| polterguy/magic Magic Cloud is a self-hosted, MIT-licensed AI app builder platform that turns plain-English prompts into full-stack applications — database… | 93 | 1194 | active |
| huggingface/llm.nvim llm.nvim is a Neovim plugin that brings LLM-powered features like ghost-text code completion to the editor, using llm-ls as its backend. It… | 73 | 1194 | active |
| Chorus-AIDLC/Chorus Chorus is a self-hosted agent harness that coordinates a team of coding agents (Claude Code, MCP-compatible agents) plus human reviewers in… | 78 | 1192 | active |
| iDC-NEU/YiGraph YiGraph is an LLM-driven agent system for autonomous graph data analytics built on the Analytics-Augmented Generation (AAG) framework. It e… | 75 | 1192 | active |
| lmstudio-ai/mlx-engine mlx-engine is the Apple MLX-based LLM inference engine that powers LM Studio on Mac, built on mlx-lm with support for vision models via mlx… | 68 | 1192 | active |
| dulikaifazr/Cougar-CLI Cougar CLI is an AI programming agent that runs in the terminal, letting developers interact with LLMs to write and manage code from the co… | 42 | 1192 | active |
| GAIR-NLP/ASI-Arch A multi-agent framework that lets an LLM autonomously conduct end-to-end research on neural network architecture discovery, specifically li… | 40 | 1192 | active |
| yjacquin/fast-mcp Fast MCP is a Ruby implementation of the Model Context Protocol (MCP), letting AI models call Ruby tools and read app resources. It support… | 45 | 1191 | active |
| linux-do/override A Go-based local proxy service that overrides GitHub Copilot's API endpoints in VSCode and JetBrains IDEs, redirecting code completion and … | 15 | 1191 | active |
| zai-org/VisualGLM-6B VisualGLM-6B is an open-source multimodal conversational language model supporting images, Chinese, and English, built on ChatGLM-6B with a… | 30 | 4154 | maintenance |
| keinsaasforever/better-chatbot Keinsaas Navigator (formerly Better Chatbot) is an open-source, self-hostable AI chatbot workspace built with Next.js and the Vercel AI SDK… | 66 | 1190 | active |
| polyuiislab/infiAgent infiAgent (MLA) is a Python agent framework for building domain-specific AI agents that run for days on complex tasks without context degra… | 66 | 1190 | active |
| ScholarXIV/OpenScholarXIV OpenScholarXIV is an open-source, AI-powered mobile app for searching, reading, bookmarking, sharing, and summarizing academic papers from … | 77 | 1189 | active |
| jncraton/languagemodels A Python library providing simple building blocks for running large language models locally with as little as 512MB of RAM. It offers instr… | 57 | 1189 | active |
| fmaclen/hollama Hollama is a minimal LLM chat application that runs entirely in the browser, connecting to Ollama and OpenAI servers with all data stored l… | 93 | 1188 | active |
| nspady/google-calendar-mcp A Model Context Protocol (MCP) server that integrates Google Calendar with AI assistants like Claude, enabling event creation, updates, del… | 85 | 1188 | active |
| Cloudflare AI A monorepo of TypeScript packages and examples for building AI-powered applications on Cloudflare. It provides Vercel AI SDK and TanStack A… | 79 | 1188 | active |
| Agent Landing Zone GPT-RAG is an Azure solution accelerator providing architecture templates and deployment assets for enterprise-scale Retrieval-Augmented Ge… | 92 | 1187 | active |
| context-labs/HALO HALO (Hierarchical Agent Loop Optimizer) is a desktop application that imports LLM agent traces from sources like Langfuse, Arize, JSONL, o… | 74 | 1187 | active |
| SamuelZ12/longcut LongCut is a Next.js web application that turns long-form YouTube videos into a structured learning workspace with AI-generated highlight r… | 61 | 1186 | active |
| composio-community/secure-openclaw A self-hostable personal AI assistant that runs 24x7 on your messaging platforms (WhatsApp, Telegram, Signal, iMessage), powered by Claude … | 55 | 1186 | active |
| MediaBrain-SJTU/MING MING (明医) is a Chinese medical consultation large language model fine-tuned on medical instruction data, with variants built on bloomz-7b a… | 37 | 1186 | active |
| DAMO-NLP-SG/VideoLLaMA3 VideoLLaMA 3 is a frontier multimodal foundation model for image and video understanding, released with checkpoints, inference code, and de… | 34 | 1186 | active |
| bodaay/HuggingFaceModelDownloader A Go-based CLI utility for downloading models and datasets from the HuggingFace Hub with parallel, resumable downloads. It includes an inte… | 96 | 1185 | active |
| Azure-Samples/chat-with-your-data-solution-accelerator A Microsoft solution accelerator that deploys a ChatGPT-style Q&A experience grounded in your own documents, using Azure OpenAI models and … | 92 | 1185 | active |
| Mibayy/token-savior Token Savior is an MCP server written in Python that provides AI coding agents like Claude with structural codebase navigation (72 tools fo… | 82 | 1185 | active |
| Foundation Models Framework A native iOS and macOS workbench app for learning, testing, and evaluating Apple's Foundation Models framework. It provides editable recipe… | 78 | 1185 | active |
| auto-novel/auto-novel AutoNovel is a website application that automatically machine-translates light novels (web novels, bunko novels, and local files) using LLM… | 76 | 1185 | active |
| HammerGPT/Hyper-Alpha-Arena A self-hosted AI-powered crypto trading platform for Hyperliquid and Binance Futures perpetual contracts. It combines LLM-driven trading ag… | 51 | 1185 | active |
| HiveNexus/HiveChat HiveChat is a self-hostable AI chat application designed for small and medium-sized teams, with multi-user management, group-based permissi… | 36 | 1185 | active |
| Gentleman-Programming/gentleman-guardian-angel Gentleman Guardian Angel (gga) is a pure-Bash CLI tool that runs AI-powered code reviews on staged files via a git pre-commit hook, using a… | 71 | 1184 | active |
| zjunlp/LightMem LightMem is a lightweight Python framework for adding long-term memory to LLM applications and AI agents, providing memory storage, retriev… | 61 | 1183 | active |
| jerry-ai-dev/MODULAR-RAG-MCP-SERVER A modular, pluggable RAG (Retrieval-Augmented Generation) framework exposed as an MCP (Model Context Protocol) server, so AI assistants lik… | 44 | 1183 | active |
| AGenUI/AGenUI AGenUI is a high-performance A2UI SDK written in C++ that renders AI-generated, streaming user interfaces as native components on iOS, Andr… | 81 | 1182 | active |
| mlfoundations/open_flamingo OpenFlamingo is an open-source PyTorch implementation of DeepMind's Flamingo, a large multimodal vision-language model that interleaves ima… | 23 | 4114 | maintenance |
| shawwn/llama-dl A shell script that provides high-speed curl-based downloads of Meta's LLaMA model weights (7B, 13B, 30B, 65B), fetching all weights in und… | 31 | 4110 | maintenance |
| Facico/Chinese-Vicuna Chinese-Vicuna is a low-resource LLaMA+LoRA solution for building Chinese instruction-following language models, structured after Alpaca. I… | 34 | 4106 | maintenance |
| hijohnnylin/neuronpedia Neuronpedia is an open source AI interpretability platform for exploring, visualizing, and steering the internals of language models. It ho… | 93 | 1178 | active |
| ref-tools/ref-tools-mcp Ref MCP is a Model Context Protocol server that gives AI coding agents fast, token-efficient access to documentation for public and private… | 62 | 1175 | active |
| princeton-nlp/MeZO MeZO is a memory-efficient zeroth-order optimizer that fine-tunes language models using only forward passes, with the same memory footprint… | 30 | 1174 | stable |
| baichuan-inc/Baichuan2 Baichuan 2 is a family of open large language models (7B and 13B, Base and Chat variants with 4-bit quantized versions) trained by Baichuan… | 28 | 4082 | maintenance |
| i-am-bee/agentstack Agent Stack is open-source infrastructure (hosted by the Linux Foundation) for turning AI agents into running HTTP services, built on the A… | 78 | 1172 | active |
| whyiyhw/chatgpt-wechat A self-hosted Go application that lets users safely use LLM assistants (ChatGPT, Gemini, DeepSeek, Dify workflows) inside WeChat by relayin… | 56 | 1172 | active |
| nv-tlabs/LLaMA-Mesh LLaMA-Mesh is a fine-tuned large language model from NVIDIA Research that generates and understands 3D meshes by representing vertex coordi… | 24 | 1172 | active |
| Ricky-7-Yan/intelligent-audit-system AuditPilot is an enterprise AI agent workbench for audit delivery, combining evidence-grounded agentic RAG, governed tool execution, evalua… | 57 | 1171 | active |
| kleneway/pastemax PasteMax is a cross-platform desktop application for browsing a repository's files, selecting relevant ones, and copying their contents for… | 56 | 1171 | active |
| 199-biotechnologies/claude-deep-research-skill A Claude Code skill (plugin) that turns the agent into an enterprise-grade deep research engine with an 8-phase pipeline covering scoping, … | 48 | 1171 | active |
| mateaix/mateclaw MateClaw is a self-hosted, team-oriented AI agent platform ('second brain') built on Spring Boot and Spring AI Alibaba, shipped as a single… | 81 | 1170 | active |
| Strands Agents Agent SOPs are markdown-based standard operating procedures that guide AI agents through complex, multi-step workflows using natural langua… | 79 | 1170 | active |
| Tencent/hpc-ops HPC-Ops is a production-grade C++/CUDA operator library for high-performance LLM inference, developed by Tencent's Hunyuan AI Infra team. I… | 58 | 1170 | active |
| BiFangKNT/mtga MTGA is a local proxy application that lets IDEs with fixed model providers (such as Trae) use arbitrary LLM backends. It exposes an OpenAI… | 70 | 1169 | active |
| parcadei/llm-tldr A Python CLI tool and daemon that indexes codebases into a 5-layer analysis stack (AST, call graph, control flow, data flow, program depend… | 10 | 1169 | active |
| heymrun/heym Heym is an AI-native, low-code workflow automation platform with a visual drag-and-drop editor for building agentic systems. It provides LL… | 78 | 1168 | active |
| GongRzhe/Gmail-MCP-Server A Model Context Protocol (MCP) server that integrates Gmail with AI assistants like Claude Desktop, featuring automatic OAuth2 authenticati… | 10 | 1168 | active |
| ModalityDance/PalmClaw PalmClaw is an open-source agent framework that runs natively on Android phones, keeping sessions, memory, skills, tools, and the agent loo… | 76 | 1166 | active |
| ztx888/HaloWebUI HaloWebUI is a self-hosted AI chat platform forked from Open WebUI, with a localized Chinese interface plus added model billing and usage s… | 49 | 1164 | active |
| IST-DASLab/marlin Marlin is a highly optimized FP16xINT4 matrix multiplication CUDA kernel for LLM inference that achieves near-ideal 4x speedups at batch si… | 27 | 1164 | active |
| chrishayuk/larql LARQL decompiles transformer models into a queryable 'vindex' (vector index) format and provides LQL, a SQL-like query language, to browse,… | 79 | 1162 | active |
| agentrq/agentrq AgentRQ is a self-hosted, human-in-the-loop task management and collaboration platform for AI agents, built around the Model Context Protoc… | 78 | 1162 | active |
| vm0-ai/vm0 VM0 (Zero) is an AI agent platform that acts as a 'trustworthy AI teammate', connecting to 1,400+ tools (Slack, Notion, Gmail, Linear, GitH… | 81 | 1161 | active |
| ricklamers/shell-ai Shell-AI (shai) is a Python CLI utility that converts natural language descriptions into shell command suggestions using LLMs via LangChain… | 44 | 1161 | active |
| Libr-AI/OpenFactVerification Loki is an open-source Python tool that automates fact verification by decomposing texts into claims, retrieving evidence via search, and u… | 16 | 1159 | active |
| character-ai/prompt-poet Prompt Poet is a Python library for designing LLM prompts using YAML and Jinja2 templates in a low-code approach. It renders dynamic, struc… | 50 | 1158 | active |
| davis7dotsh/better-context btca (better-context) is a codebase research tool that lets developers and AI coding agents ask questions about libraries and frameworks by… | 47 | 1158 | active |
| zylos-ai/zylos-core Zylos is an open-source agent infrastructure that gives LLM-based AI assistants persistent memory, multi-channel communication (Telegram, L… | 82 | 1157 | active |
| Quorinex/Kiro-Go A Go service that converts Kiro accounts into OpenAI- and Anthropic-compatible API endpoints, with multi-account pooling, round-robin load … | 55 | 1157 | active |
| jingcheng-chen/rhinomcp RhinoMCP is a plugin and MCP server that connects Rhino 3D (and Grasshopper) to AI agents like Claude and Cursor via the Model Context Prot… | 86 | 1155 | active |
| AI-QL/tuui TUUI is an open-source desktop MCP client and local AI playground built with Vue3 and Electron, serving as a unified interface for Model Co… | 68 | 1154 | active |
| OpenGVLab/VisionLLM VisionLLM is a series of open-source multimodal large language models from OpenGVLab that unify vision-centric tasks under language instruc… | 30 | 1153 | active |
| shyamsn97/mario-gpt MarioGPT is a Python library and finetuned GPT2 model that generates playable Super Mario Bros levels from text prompts. It accompanies the… | 22 | 1152 | active |
| hexabot-ai/Hexabot Hexabot is a self-hosted, fair-core AI workflow automation platform that combines YAML-defined agentic workflows, actions, memory, RAG, and… | 64 | 1151 | active |
| Woolverine94/biniou biniou is a self-hosted web UI for 30+ generative AI models covering image, video, audio, and text generation, built with Gradio and Huggin… | 62 | 1151 | active |
| apple/ml-clara CLaRa is Apple's open-source end-to-end Retrieval-Augmented Generation model that compresses documents into continuous latent representatio… | 59 | 1151 | active |
| GENEXIS-AI/chromex Chromex is a Chrome MV3 side-panel extension that connects the browser to OpenAI's Codex CLI via a local native-messaging bridge. It lets u… | 66 | 1150 | active |
| KroMiose/nekro-agent NekroAgent is a cross-platform AI agent framework for multi-user chat scenarios that generates and executes code in sandboxed containers, w… | 83 | 1149 | active |
| Gen-Verse/LatentMAS LatentMAS is a training-free multi-agent reasoning framework that lets LLM agents collaborate in continuous latent space by passing hidden-… | 53 | 1149 | active |
| agent-topia/evolving_personality JPAF is a Python framework that gives LLM agents structured, evolving MBTI personalities based on Carl Jung's psychological types. It uses … | 45 | 1149 | active |
| brightmart/albert_zh A repository providing pre-trained ALBERT models for Chinese language, implemented in TensorFlow with PyTorch and Keras conversions. It inc… | 32 | 3984 | maintenance |
| amazon-science/mm-cot Official PyTorch implementation of the paper 'Multimodal Chain-of-Thought Reasoning in Language Models', which adds vision features to a tw… | 31 | 3978 | maintenance |
| LiuMengxuan04/MiniCode MiniCode is a lightweight terminal-based AI coding assistant that implements a Claude Code-like agent loop with tool calling, diff review, … | 59 | 1147 | active |
| mtymek/opencode-obsidian An Obsidian plugin that embeds the OpenCode AI assistant's web view directly into Obsidian's sidebar, launching it via Node.js child proces… | 57 | 1147 | active |
| mrkrsl/web-search-mcp A locally hosted MCP (Model Context Protocol) server written in TypeScript that gives local LLMs web search capabilities without requiring … | 33 | 1147 | active |
| tontinton/maki Maki is a terminal-based AI coding agent written in Rust, optimized for minimal context token usage with tools like tree-sitter file indexi… | 77 | 1146 | active |
| agentbay-ai/wuying-agentbay-sdk Multi-language SDK (Python, TypeScript, Go, Java) for Wuying AgentBay, Alibaba Cloud's cloud sandbox platform built for AI agents. It lets … | 70 | 1146 | active |
| MoonshotAI/MoonEP MoonEP is an Expert Parallelism communication library for Mixture-of-Experts training that keeps token loads perfectly balanced across rank… | 56 | 1146 | active |
| terobox/ChatGPT-API-Faucet The frontend code for ChatGPT API Faucet, a public-welfare website where AI developers can claim $1.00 of free API tokens every 24 hours fo… | 32 | 1146 | active |
| Ryandonofrio3/osgrep osgrep is a local, grep-like semantic search CLI for codebases, built for AI coding agents. It uses local embeddings (ColBERT via onnxrunti… | 47 | 1145 | active |