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 |
|---|---|---|---|
| openlm-research/open_llama OpenLLaMA is a permissively licensed (Apache-2.0) open reproduction of Meta AI's LLaMA, releasing 3B, 7B, and 13B pretrained model weights … | 30 | 7527 | maintenance |
| szczyglis-dev/py-gpt PyGPT is an open-source, all-in-one desktop AI assistant for Linux, Windows, and Mac, written in Python. It supports chat, agents, vision, … | 93 | 1973 | active |
| SaiAkhil066/CORTEX-AI-SUPER-RAG CORTEX RAG is a local-first, agentic retrieval-augmented generation application that lets users upload PDFs and ask questions with cited an… | 64 | 1973 | active |
| jd-opensource/JoyAI-VL-Interaction JoyAI-VL-Interaction is an open 8B-scale vision-language interaction model with a complete deployable real-time streaming system, including… | 59 | 1970 | active |
| StarCoder StarCoder is a 15B-parameter code language model trained on 80+ programming languages, and this repository hosts the fine-tuning and infere… | 30 | 7501 | maintenance |
| ROCm/FastFlowLM FastFlowLM (FLM) is an NPU-first LLM inference runtime purpose-built and deeply optimized for AMD Ryzen AI NPUs (XDNA2), offering an Ollama… | 87 | 1967 | active |
| StanfordBDHG/HealthGPT HealthGPT is an experimental open-source iOS app built on the Stanford Spezi framework that lets users query their Apple Health data using … | 77 | 1965 | active |
| mlc-ai/xgrammar XGrammar is an open-source library for efficient, flexible, and portable structured generation in LLM inference via constrained decoding. I… | 91 | 1964 | active |
| Agent Shell agent-shell is an Emacs Lisp package that provides a native Emacs buffer interface for interacting with LLM coding agents (Claude Code, Ope… | 63 | 1962 | active |
| OpenAI ChatKit ChatKit is OpenAI's batteries-included framework for building AI-powered chat experiences, providing a production-ready chat interface with… | 75 | 1958 | active |
| Yuliang-Liu/Monkey Monkey is a large multi-modal model (LMM) research project from CVPR 2024 that improves image understanding via higher input resolution and… | 71 | 1956 | active |
| huggingface/chat-macOS HuggingChat macOS is a native Swift chat application for macOS that provides access to open-source AI chat models from Hugging Face. It off… | 10 | 1954 | active |
| MicrosoftDocs/mcp Microsoft's official Model Context Protocol (MCP) server and CLI that gives LLMs and AI agents real-time access to trusted Microsoft Learn … | 64 | 1951 | active |
| deepseek-ai/TileKernels TileKernels is a Python library of optimized GPU kernels for LLM operations, written in the TileLang DSL. It provides kernels for MoE routi… | 58 | 1949 | active |
| Darkatse/TauriTavern TauriTavern is a native rewrite of SillyTavern built with Tauri v2 and a Rust backend, providing the classic LLM chat/roleplay frontend as … | 86 | 1948 | active |
| microsoft/Magma Magma is Microsoft Research's foundation model for multimodal AI agents, released as an 8B vision-language model that understands images an… | 50 | 1948 | active |
| kyegomez/BitNet A PyTorch implementation of the BitNet architecture from the paper 'BitNet: Scaling 1-bit Transformers for Large Language Models', providin… | 73 | 1947 | active |
| hank9999/kiro.rs A Rust-based proxy service that exposes an Anthropic Claude API-compatible endpoint and translates requests to the Kiro API. It supports SS… | 72 | 1947 | active |
| BytedTsinghua-SIA/DAPO DAPO is an open-source reinforcement learning system for large-scale LLM training, released by ByteDance Seed and Tsinghua AIR. It implemen… | 26 | 1946 | active |
| oficcejo/aiagents-stock A Python multi-AI-agent stock analysis and monitoring system for mainland China A-shares, simulating a team of securities analysts to produ… | 52 | 1945 | active |
| OpenBMB/StaffDeck StaffDeck is an open-source enterprise platform for building and managing AI-powered digital employees that codify professional experience,… | 78 | 1944 | active |
| databricks-solutions/ai-dev-kit A Databricks Field Engineering toolkit that provides skills, an MCP server, and a Builder App for AI coding agents working with the Databri… | 75 | 1942 | active |
| NVIDIA-AI-Blueprints/video-search-and-summarization NVIDIA's GPU-accelerated AI Blueprint reference architecture for building video analytics agents that search, summarize, and reason over li… | 86 | 1938 | active |
| carlrobertoh/ProxyAI ProxyAI is an open-source AI coding copilot plugin for JetBrains IDEs like IntelliJ and PyCharm. It connects to models from OpenAI, Anthrop… | 75 | 1935 | active |
| wuyoscar/Internal-Safety-Collapse ISC-Bench/TVD is a research framework for studying 'Internal Safety Collapse' in frontier LLMs, where agents placed in adversarial codespac… | 60 | 1935 | active |
| severity1/claude-code-prompt-improver A Claude Code hook plugin that intelligently improves prompts at submit time, tool use, and subagent start, injecting contextual nudges so … | 68 | 1932 | active |
| SMNETSTUDIO/WeChat-AI A self-hosted WeChat roleplay chatbot service written in TypeScript that connects directly to Tencent iLink, stores data in remote Redis, a… | 65 | 1931 | active |
| YoMo YoMo is an open-source serverless LLM function calling framework for building fast, geo-distributed AI agents, written in Rust with a QUIC-… | 97 | 1929 | active |
| skalesapp/skales Skales is a personal AI agent desktop and mobile application that runs locally on Windows, macOS, Linux, Android, and iOS, executing multi-… | 80 | 1924 | active |
| MaximeRivest/riddle A diary-style application for the reMarkable Paper Pro e-ink tablet that turns handwritten pages into conversations with an LLM. You write … | 69 | 1922 | active |
| microsoft/sample-app-aoai-chatGPT A Microsoft sample web chat application that connects to Azure OpenAI chat models, including support for the 'On Your Data' feature with da… | 10 | 1922 | active |
| IPADS-SAI/MobiAgent MobiAgent is a systematic framework for building customizable GUI agents that operate mobile phones, comprising the MobiMind agent model fa… | 54 | 1920 | active |
| yologdev/yoyo-evolve yoyo is an open-source terminal coding agent written in Rust that autonomously evolves its own source code — reading its code, planning imp… | 83 | 1917 | active |
| LeapLabTHU/Absolute-Zero-Reasoner Official implementation of Absolute Zero Reasoner (AZR), a system that trains LLM reasoning via reinforced self-play with zero external dat… | 33 | 1916 | active |
| alexpinel/Dot Dot is a standalone Electron desktop application for chatting with your documents using fully local LLMs and Retrieval Augmented Generation… | 16 | 1915 | active |
| Dicklesworthstone/pi_agent_rust pi_agent_rust is a native, single-binary AI coding agent CLI written in Rust with zero unsafe code, ported from Mario Zechner's Pi Agent. I… | 83 | 1914 | active |
| deepseek-ai/DeepSeek-LLM DeepSeek LLM is a family of open-source large language models (7B and 67B, Base and Chat variants) trained from scratch on 2 trillion token… | 27 | 7251 | maintenance |
| zzet/gortex Gortex is a high-performance code-intelligence engine that indexes codebases into a persistent knowledge graph using tree-sitter AST analys… | 78 | 1911 | active |
| AiPPT AiPPT (文多多) is a commercial-grade AI PowerPoint generation project that creates presentations from topics, files, or URLs, and can parse PP… | 46 | 1910 | active |
| Ollamac Ollamac is a native macOS application that provides a chat interface for interacting with local Ollama models. It supports all Ollama model… | 30 | 1910 | active |
| hanshuaikang/nezha Nezha is a lightweight cross-platform desktop IDE designed for the AI coding era, letting you run and monitor multiple Claude Code and Code… | 79 | 1907 | active |
| showlab/ShowUI ShowUI is an open-source, lightweight 2B vision-language-action model for GUI agents and computer use, accepted at CVPR 2025. The repositor… | 54 | 1906 | active |
| melih-unsal/DemoGPT DemoGPT is a Python framework and autonomous agent that generates LangChain-based LLM agent applications from natural-language prompts, bun… | 51 | 1906 | active |
| AutoFigure AutoFigure-Edit is a Python application that converts scientific paper method sections into fully editable SVG figures using large language… | 53 | 1905 | active |
| ShenSeanChen/waku-agent Waku Agent is a local-first AI agent harness in Python that exposes the full agent stack — harness, loop, memory, and eval/LLM-Ops — as sma… | 79 | 1903 | active |
| Yuan-lab-LLM/ClawManager ClawManager is a Kubernetes-native control plane for managing AI agent instances at cluster scale, providing governed AI access through an … | 81 | 1900 | active |
| BidingCC/BuildingAI BuildingAI is an open-source, enterprise-grade platform for visually assembling AI applications without code, described as the 'WordPress o… | 80 | 1900 | active |
| policy-gradient/GRPO-Zero A minimal from-scratch Python implementation of DeepSeek's GRPO (Group Relative Policy Optimization) algorithm for reinforcement learning t… | 24 | 1899 | active |
| google-deepmind/penzai Penzai is a JAX research toolkit for building, editing, and visualizing neural networks as legible, functional pytree data structures. It i… | 10 | 1899 | active |
| vllm-project/vllm-metal A community-maintained hardware plugin that enables vLLM to run LLM inference on Apple Silicon Macs using MLX as the primary compute backen… | 80 | 1898 | active |
| 7836246/cursor2api A self-hosted proxy service that converts Cursor's free documentation-page AI chat endpoint into OpenAI Chat Completions and Anthropic Mess… | 10 | 1896 | active |
| ivanfioravanti/chatbot-ollama An open-source web-based chat UI for Ollama, forked from chatbot-ui, that lets users chat with locally hosted LLMs. It supports document (P… | 44 | 1895 | active |
| bhaskatripathi/pdfGPT pdfGPT is an open-source Python application that lets users chat with the contents of PDF files using GPT capabilities. It implements a sim… | 59 | 7162 | maintenance |
| MrGeDiao/shuorenhua A Chinese-first rewrite skill that removes AI-generated tone (template phrasing, performative language, translationese) from text while pre… | 79 | 1891 | active |
| SqueezeAILab/LLMCompiler LLMCompiler is a Python framework from an ICML 2024 paper that orchestrates parallel function calling with LLMs. It uses a planner, task fe… | 27 | 1889 | active |
| netease-youdao/BCEmbedding BCEmbedding is NetEase Youdao's open-source library of bilingual and crosslingual embedding and reranker models for English and Chinese, bu… | 68 | 1881 | active |
| ginlix-ai/LangAlpha LangAlpha is an open-source agentic AI harness for financial market research and investment decision support, inspired by code-agent harnes… | 83 | 1880 | active |
| nndeploy/nndeploy nndeploy is an easy-to-use, high-performance AI deployment framework written in C++ with Python bindings. It provides a visual drag-and-dro… | 81 | 1880 | active |
| Datahike Datahike is a durable, versioned Datalog database with Datomic-compatible APIs and git-like semantics, built on persistent data structures … | 93 | 1877 | active |
| Jido Jido is an autonomous agent framework for Elixir that runs agents as supervised BEAM processes with fault tolerance, signal-based coordinat… | 81 | 1875 | active |
| THUDM/LongWriter LongWriter is a research project from Tsinghua's THUDM group providing fine-tuned LLMs (based on GLM-4-9B and Llama-3.1-8B) plus training a… | 33 | 1874 | active |
| chatgpt-web-dev/chatgpt-web A self-hosted third-party ChatGPT web UI built with Express (Node.js backend) and Vue3 (frontend), calling the official OpenAI completion A… | 70 | 1873 | active |
| e-p-armstrong/augmentoolkit Augmentoolkit is a Python application that generates domain-expert fine-tuning datasets from uploaded documents and trains custom LLMs on t… | 65 | 1872 | active |
| PRIME-RL/PRIME PRIME (Process Reinforcement through Implicit Rewards) is an open-source Python framework for online reinforcement learning with process re… | 23 | 1872 | active |
| dphnAI/sonar Sonar is a large-scale LLM inference engine for Hugging Face-compatible language and multimodal models, based on vLLM (formerly the Aphrodi… | 92 | 1871 | active |
| zhu1090093659/deepseek-pp DeepSeek++ is an open-source browser extension for Chrome, Edge, and Firefox that turns the DeepSeek web app into an AI agent workspace. It… | 10 | 1870 | active |
| korotovsky/slack-mcp-server A Model Context Protocol (MCP) server for Slack workspaces written in Go, exposing Slack channels, DMs, group DMs, search, and smart histor… | 72 | 1869 | active |
| AkaliKong/MiniOneRec MiniOneRec is an open-source framework for generative recommendation built on large language models, covering the full pipeline of semantic… | 59 | 1868 | active |
| jiujiu532/grok2api A self-hosted Python/FastAPI gateway that exposes grok.com and console.x.ai chat, image, and video capabilities through OpenAI- and Anthrop… | 52 | 1867 | active |
| stephengpope/thepopebot A self-hosted autonomous AI agent platform that combines chat (Telegram and web), coding agents (Claude Code, Codex, Gemini, etc.), and liv… | 64 | 1862 | active |
| AminForou/mcp-gsc A Model Context Protocol (MCP) server that connects Google Search Console to AI assistants like Claude Desktop, Cursor, and other MCP clien… | 63 | 1862 | active |
| MixLabPro/comfyui-mixlab-nodes A ComfyUI custom-nodes plugin that adds workflow-to-web-app conversion, screen sharing, floating video, GPT/LLM integration, 3D, speech rec… | 53 | 1862 | active |
| HITsz-TMG/VideoClaw VideoClaw is an AI director system that turns a one-line idea or story synopsis into a fully automated video production pipeline, covering … | 64 | 1861 | active |
| questflowai/investorskills An open-source library of portable, plain-text 'investor skill' packages (SKILL.md files plus investment schemas) that encode the judgment … | 55 | 1861 | active |
| superagent-ai/vibekit VibeKit is a CLI tool that wraps AI coding agents such as Claude Code, Gemini CLI, Grok CLI, and Codex in isolated Docker sandboxes with au… | 46 | 1860 | active |
| laekov/fastmoe FastMoE is a PyTorch library providing efficient Mixture of Experts (MoE) layers with custom C/CUDA operators. It supports distributed expe… | 23 | 1860 | active |
| OpenNMT OpenNMT is an open-source ecosystem for neural machine translation and sequence learning, with PyTorch (OpenNMT-py) and TensorFlow (OpenNMT… | 40 | 7018 | maintenance |
| u14app/neo-chat Neo Chat is a self-hostable, local-first AI chat workspace built with Next.js, React, and TypeScript. It combines multi-provider chat, agen… | 91 | 1859 | active |
| webpilot-ai/Webpilot Webpilot is a free, open-source browser extension that acts as a 'Copilot for the web', letting users converse with web page content withou… | 72 | 1859 | active |
| openreasoner/openr OpenR is an open-source Python framework that integrates search, reinforcement learning, and process supervision to improve chain-of-though… | 23 | 1859 | active |
| RanFeng/clipsketch-ai ClipSketch AI is a web-based AI content creation workbench that imports videos from Bilibili and Xiaohongshu links, lets users frame-accura… | 38 | 1858 | active |
| sunmh207/AI-Codereview-Gitlab A self-hosted automated code review application that uses large language models (DeepSeek, OpenAI, Anthropic, ZhipuAI, Qwen, Ollama) to rev… | 81 | 1857 | active |
| Tele-AI/Telechat TeleChat is a family of open-source bilingual (Chinese-English) large language models (1B, 7B, 12B) developed by China Telecom's AI team, r… | 64 | 1852 | active |
| GuDaStudio/GrokSearch GrokSearch is an MCP server built on FastMCP that gives Claude Code and other LLM clients real-time web access via a dual-engine architectu… | 45 | 1852 | active |
| Kav-K/GPTDiscord GPTDiscord is a self-hosted Discord bot providing an all-in-one GPT interface with ChatGPT-style conversations, DALL-E image generation, AI… | 100 | 1850 | active |
| nimbalyst/nimbalyst Nimbalyst is an open-source (MIT) Electron desktop app that serves as a visual workspace for running AI coding agents like Claude Code, Cod… | 83 | 1850 | active |
| Hermes HUD A browser-based dashboard for monitoring the Hermes AI agent, exposing its memory, sessions, costs, health, plugins, and governance data ac… | 82 | 1850 | active |
| HKUDS/OpenOPC OpenOPC is a Python framework for building a personal AI-native company that recruits role-specific AI employees, assigns and hands off tas… | 56 | 1848 | active |
| aallam/openai-kotlin A Kotlin client library for the OpenAI API built on Kotlin multiplatform and coroutines, using Ktor as the HTTP engine. It provides typed a… | 57 | 1847 | active |
| Datus-ai/Datus-agent Datus is an open-source (Apache-2.0) AI data engineering agent delivered primarily as a Python CLI, with a VS Code/Cursor extension and opt… | 85 | 1845 | active |
| shiwenwen/hope-agent Hope Agent is a local-first, cross-device desktop AI assistant built with Rust and Tauri that features long-term memory, autonomous goal pu… | 78 | 1843 | active |
| YangLing0818/RPG-DiffusionMaster Official implementation of RPG (Recaption, Plan, Generate), a training-free framework that uses multimodal LLMs as prompt recaptioners and … | 26 | 1842 | active |
| abinthomasonline/repo2txt A browser-based tool that converts GitHub, GitLab, Azure DevOps repositories, local folders, or ZIP files into a single formatted text file… | 63 | 1837 | active |
| trpc-group/trpc-agent-go tRPC-Agent-Go is a Go-native framework for building production LLM agent systems, offering agents, graph workflows (LangGraph-equivalent), … | 79 | 1836 | active |
| he-yufeng/CoreCoder CoreCoder is a minimal AI coding agent written in roughly 1,000 lines of Python, inspired by Claude Code and designed to work with any LLM.… | 82 | 1833 | active |
| tile-ai/TileRT TileRT is a tile-based runtime for ultra-low-latency LLM inference, achieving hundreds to over 1000 tokens/s decode speeds on frontier mode… | 75 | 1831 | active |
| a5c-ai/babysitter Babysitter is an npm-distributed CLI and runtime that enforces deterministic, step-by-step process control on AI coding agents across 12 su… | 72 | 1831 | active |
| OpenAgentPlatform/Dive Dive is an open-source MCP host desktop application that connects to any LLM supporting function calling, including ChatGPT, Anthropic, Oll… | 75 | 1828 | active |
| beam-cloud/beta9 Beam (beta9) is an open-source serverless runtime for AI workloads, providing GPU inference endpoints, isolated sandboxes for running untru… | 91 | 1827 | active |
| evalplus/evalplus EvalPlus is a Python framework and benchmark suite for rigorously evaluating LLM-synthesized code, providing HumanEval+ and MBPP+ datasets … | 37 | 1826 | active |