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 |
|---|---|---|---|
| andrewyng/aisuite aisuite is a lightweight Python library providing a unified, OpenAI-style Chat Completions API across many LLM providers (OpenAI, Anthropic… | 81 | 16320 | active |
| MNN MNN is a lightweight, high-performance deep learning inference engine developed by Alibaba, supporting LLMs, vision, audio, and multimodal … | 90 | 16188 | active |
| raga-ai-hub/RagaAI-Catalyst RagaAI Catalyst is a Python SDK for observability, monitoring, and evaluation of LLM and agentic AI applications, with tracing of agents, L… | 52 | 16164 | active |
| HKUDS/OpenHarness OpenHarness is a lightweight open-source agent harness in Python providing tool use, skills, memory, and multi-agent coordination, launched… | 64 | 15994 | active |
| opensandbox-group/OpenSandbox OpenSandbox is a general-purpose sandbox platform for AI applications that securely runs commands, code interpreters, browsers, and develop… | 80 | 15952 | active |
| chatfire-AI/huobao-drama Huobao Drama is a self-hosted, AI-powered end-to-end short drama generation platform that automates the full pipeline from a one-sentence i… | 82 | 15921 | active |
| Outlines Outlines is a Python library for structured generation that guarantees LLM outputs conform to a desired structure (JSON schemas, regex, gra… | 93 | 15920 | active |
| kubeflow/kubeflow Kubeflow is a CNCF-graduated, Kubernetes-native toolkit for building AI/ML platforms, comprising subprojects like Pipelines, Notebooks, Tra… | 78 | 15915 | stable |
| vibrantlabsai/ragas Ragas is a Python library for evaluating LLM applications with objective, LLM-driven metrics and systematic experiment loops. It also gener… | 66 | 15901 | active |
| coderamp-labs/gitingest Gitingest turns any Git repository into a prompt-friendly text digest of its codebase, suitable for feeding into LLMs. It is available as a… | 68 | 15879 | active |
| GeeeekExplorer/nano-vllm A lightweight vLLM-style LLM inference engine implemented from scratch in about 1,200 lines of Python. It offers fast offline inference wit… | 51 | 15834 | active |
| modelscope/ms-swift ms-swift is a ModelScope community framework for fine-tuning, inference, evaluation, quantization, and deployment of 600+ text LLMs and 400… | 90 | 15809 | active |
| YishenTu/claudian Claudian is an Obsidian plugin that embeds AI coding agents like Claude Code, Codex, Grok, and OpenCode directly into your vault. It turns … | 80 | 15722 | active |
| mindverse/Second-Me Second Me is an open-source platform for training a personal AI self from your own memories using hierarchical memory modeling and alignmen… | 38 | 15682 | active |
| plandex-ai/plandex Plandex is an open-source, terminal-based AI coding agent that plans and executes large, multi-step coding tasks across many files in real-… | 46 | 15656 | active |
| AgriciDaniel/claude-obsidian A Claude Code plugin/skill system that turns an Obsidian vault into a self-organizing AI second brain. It captures sources, creates linked … | 81 | 15587 | active |
| Unstructured Unstructured is an open-source ETL library and platform for converting complex documents (PDF, DOCX, HTML, images, and 65+ file types) into… | 95 | 15556 | active |
| eigent-ai/eigent Eigent is an open-source desktop application for building and running AI agent workforces that automate complex multi-step workflows. Built… | 85 | 15506 | active |
| ggml-org/ggml ggml is a plain C/C++ tensor library for machine learning with no dependencies, designed to be simple, portable, and efficient. It supports… | 99 | 15480 | stable |
| yc-software/qm QM is a self-hostable multiplayer agent harness that lets every employee in a company work with AI agents in personal and shared scopes acr… | 80 | 15434 | active |
| superset-sh/superset Superset is an agentic desktop IDE for macOS that orchestrates 100+ CLI-based coding agents (Claude Code, Codex, Cursor Agent, OpenCode) in… | 81 | 15345 | active |
| GaiZhenbiao/ChuanhuChatGPT Chuanhu Chat is a Python/Gradio-based web GUI for chatting with ChatGPT and many other LLMs (GPT-5/4, Claude, Gemini, ChatGLM, Llama, Ollam… | 64 | 15269 | active |
| yusufkaraaslan/Skill_Seekers Skill Seekers is a Python CLI toolkit and MCP server that converts documentation sites, GitHub repos, PDFs, codebases, notebooks, and other… | 83 | 15096 | active |
| ConardLi/easy-dataset Easy Dataset is a self-hosted web application for building high-quality structured datasets for LLM fine-tuning, RAG, and model evaluation.… | 66 | 14989 | active |
| Botpress Botpress is an open-source platform and hub for building, deploying, and managing GPT/LLM-powered chatbots and AI agents, with a visual stu… | 67 | 14946 | active |
| livekit/agents LiveKit Agents is an open-source framework for building realtime, multimodal voice AI agents that run as programmable participants in LiveK… | 91 | 14870 | active |
| NVIDIA/TensorRT-LLM NVIDIA's TensorRT-LLM is a Python library and runtime for defining and serving Large Language Models with state-of-the-art inference optimi… | 83 | 14851 | active |
| llmware-ai/llmware llmware is a Python framework for building enterprise RAG pipelines and LLM-based applications using small, specialized open-source models.… | 90 | 14816 | active |
| mindfold-ai/Trellis Trellis is an open-source engineering framework and agent harness for AI coding assistants that persists project specs, tasks, and cross-se… | 58 | 14748 | active |
| RWKV RWKV is a novel language model architecture that combines RNN efficiency (linear time, constant memory, no KV-cache) with transformer-level… | 66 | 14744 | active |
| SesameAILabs/csm CSM (Conversational Speech Model) is Sesame's speech generation model that produces conversational audio from text and audio context, using… | 27 | 14728 | active |
| microsoft/RD-Agent RD-Agent is a Microsoft open-source framework that uses LLM-powered agents to automate research and development processes such as factor mi… | 69 | 14698 | active |
| NanmiCoder/cc-haha A local-first cross-platform desktop workspace for Claude Code and AI coding agents, built with Electron, React, and TypeScript. It provide… | 80 | 14671 | active |
| AI Scientist The AI Scientist is a system that uses large language models to autonomously perform end-to-end scientific research, from idea generation a… | 46 | 14620 | active |
| aiming-lab/AutoResearchClaw AutoResearchClaw is a Python framework for fully autonomous, self-evolving research that takes an idea from chat to a generated paper using… | 70 | 14582 | active |
| FreeToken FreeToken is an edge-native Mixture-of-Experts (MoE) LLM serving engine that runs frontier-scale open-weight models on consumer hardware by… | 79 | 14561 | active |
| Casdoor Casdoor is an open-source, self-hosted Identity and Access Management (IAM) and single sign-on (SSO) platform with a web UI, written in Go.… | 94 | 14524 | active |
| NevaMind-AI/memU memU is a lightweight, agent-driven memory system that gives LLM agents a shared, inspectable personal memory layer across sessions, agents… | 74 | 14425 | active |
| fathah/hermes-desktop Hermes One is a community-maintained native desktop app (Electron + React + TypeScript) for installing, configuring, and chatting with the … | 80 | 14407 | active |
| lsdefine/GenericAgent GenericAgent is a minimal self-evolving autonomous agent framework (~3K lines of seed code) that gives any LLM system-level control over a … | 80 | 14332 | active |
| ArangoDB ArangoDB is a native multi-model database server written in C++ that unifies graph, document (JSON), key-value, full-text, and vector searc… | 77 | 14283 | stable |
| EleutherAI/lm-evaluation-harness A Python framework for few-shot evaluation of language models across hundreds of standard benchmarks (HellaSwag, MMLU, BIG-Bench, etc.). It… | 91 | 14198 | active |
| netease-youdao/QAnything QAnything is a local knowledge base question-answering system by NetEase Youdao that supports uploading and querying various document forma… | 61 | 14188 | active |
| Microsoft Agent Framework Microsoft Agent Framework (MAF) is an open-source, multi-language framework for building, orchestrating, and deploying production-grade AI … | 82 | 13999 | active |
| Instructor Instructor is a Python library that patches LLM clients to return validated, type-safe structured data using Pydantic models, with automati… | 94 | 13980 | stable |
| andrewyng/context-hub Context Hub (chub) is an npm-distributed CLI that gives coding agents curated, versioned, language-specific API documentation stored as mar… | 54 | 13976 | active |
| Open-LLM-VTuber Open-LLM-VTuber is a cross-platform AI companion application that enables real-time voice conversations with LLMs, featuring a Live2D avata… | 62 | 13896 | active |
| BrowserOS BrowserOS is an open-source, Chromium-based agentic browser that lets AI agents (Claude Code, Codex, Cursor, MCP agents) drive a real brows… | 82 | 13886 | active |
| semantica-agi/semantica Semantica is a Python library providing graph-native infrastructure for building context graphs, knowledge graphs, and decision intelligenc… | 84 | 13821 | active |
| nanobrowser/nanobrowser Nanobrowser is an open-source Chrome extension that provides AI-powered web automation through a multi-agent system (Planner, Navigator, et… | 67 | 13818 | active |
| Lightning-AI/litgpt LitGPT is a Python library providing from-scratch, hackable implementations of 20+ open-source large language models with recipes for pretr… | 87 | 13718 | active |
| miuuyy/codex-chatgpt-web A local bridge application that exposes ChatGPT Web (including Pro tiers) as a native model inside the OpenAI Codex app, routing model turn… | 80 | 13664 | active |
| CodebuffAI/freebuff Freebuff is a free AI coding agent available as a desktop app, CLI, web builder, cloud IDE, and chat interface, funded by text ads instead … | 73 | 13614 | active |
| XiaomiMiMo/MiMo-Code MiMoCode is a terminal-native AI coding assistant that can read and write code, run commands, manage Git, and maintain persistent project m… | 79 | 13584 | active |
| Cactus Needle 2 is a 45M-parameter open language model packaged as a single 14MB binary for tool calling, device use, and structured extraction on… | 60 | 13581 | active |
| Fay Digital Human Framework Fay is an open-source Python digital human framework that connects 2.5D/3D/mobile/web digital humans or OpenAI-compatible LLMs to business … | 75 | 13549 | active |
| nidhinjs/prompt-master A Claude skill (plugin) that generates and refines precise prompts for a wide range of AI tools like ChatGPT, Cursor, Midjourney, and Stabl… | 56 | 13535 | active |
| huggingface/speech-to-speech A low-latency, fully modular voice-agent pipeline (VAD -> STT -> LLM -> TTS) built from open-source models, exposed via the OpenAI Realtime… | 85 | 13485 | active |
| EverMind-AI/EverOS EverOS is a Python library and local-first memory runtime that gives AI agents a portable, user-owned memory layer across apps, tools, and … | 83 | 13408 | active |
| Untrivial-ai/agent-orchestrator Agent Orchestrator (AO) is a local desktop IDE for supervising fleets of AI coding agents like Claude Code, Codex, and Aider. It plans task… | 79 | 13330 | active |
| cloudwego/eino Eino is a Go-based framework for building LLM and AI applications, inspired by LangChain and LlamaIndex but following Go conventions. It pr… | 84 | 13269 | active |
| LangChain4j LangChain4j is an open-source Java library for building LLM-powered applications on the JVM, providing a unified API over 20+ LLM providers… | 97 | 13266 | active |
| InsForge/InsForge InsForge is an open-source, all-in-one backend platform (BaaS) designed for AI coding agents, bundling Postgres, auth, storage, realtime, e… | 86 | 13129 | active |
| Portkey AI Gateway Portkey AI Gateway is an open-source, TypeScript-based AI gateway that routes requests to 1,600+ LLMs across many providers through a singl… | 71 | 13079 | active |
| deepseek-ai/FlashMLA FlashMLA is DeepSeek's library of optimized CUDA attention kernels implementing Multi-head Latent Attention (MLA), including dense and toke… | 64 | 13063 | active |
| ShishirPatil/gorilla Gorilla is a UC Berkeley research project for training and evaluating LLMs to make function/tool calls, including the OpenFunctions fine-tu… | 52 | 13044 | active |
| Orchestra-Research/AI-Research-SKILLs An open-source library of ~98 packaged 'skills' (knowledge modules) that turn AI coding agents like Claude Code, Codex, or Gemini into auto… | 69 | 12991 | active |
| PaddlePaddle/PaddleFormers PaddleFormers is a Transformers-style library built on PaddlePaddle providing a model zoo of 100+ large language models and vision-language… | 88 | 12983 | active |
| txtai txtai is an all-in-one open-source AI framework for semantic search, LLM orchestration and language model workflows, built around an embedd… | 95 | 12978 | active |
| PaddlePaddle/PaddleNLP PaddleNLP is an easy-to-use NLP and large language model development kit built on the PaddlePaddle deep learning framework, with a large pr… | 59 | 12977 | active |
| StarTrail-org/LEANN LEANN is a low-storage vector index that enables retrieval-augmented generation (RAG) on personal devices by recomputing embeddings on the … | 85 | 12966 | active |
| Pocket Flow An AI agent built with the Pocket Flow LLM framework that crawls GitHub repositories, analyzes codebases to identify core abstractions, and… | 55 | 12683 | active |
| Open Deep Research An open-source deep research agent built with LangGraph that performs multi-step web research using configurable LLM providers, search tool… | 10 | 12680 | active |
| Wei-Shaw/claude-relay-service A self-hosted relay/proxy service for Claude Code (and OpenAI, Gemini, Droid) subscriptions that lets multiple users share accounts via ind… | 83 | 12667 | active |
| sapientinc/HRM Official PyTorch implementation of the Hierarchical Reasoning Model (HRM), a 27M-parameter recurrent architecture with high-level and low-l… | 49 | 12642 | active |
| nearai/ironclaw IronClaw is an open-source, Rust-based 'Agent OS' and personal AI assistant that runs locally or on NEAR AI Cloud, with a WebUI, terminal, … | 79 | 12629 | active |
| langgptai/LangGPT LangGPT is a structured, reusable prompt design framework for large language models, offering template-based methodology with variables, co… | 73 | 12612 | active |
| axolotl-ai-cloud/axolotl Axolotl is a free, open-source, config-driven framework for fine-tuning large language models, supporting SFT, preference learning (DPO/KTO… | 98 | 12591 | active |
| zilliztech/claude-context Claude Context is an MCP plugin that adds semantic code search to Claude Code and other AI coding agents, indexing an entire codebase into … | 57 | 12587 | active |
| LLM A CLI tool and Python library for running prompts against large language models from OpenAI, Anthropic, Google, and many other providers, i… | 95 | 12559 | stable |
| BentoML OpenLLM is a Python framework and CLI for self-hosting open-source large language models (Llama, DeepSeek, Qwen, Mistral, etc.) as OpenAI-c… | 76 | 12552 | active |
| Chainlit/chainlit Chainlit is an open-source Python framework for building production-ready conversational AI applications with a built-in chat UI. It provid… | 94 | 12506 | active |
| hangwin/mcp-chrome A Chrome extension that acts as a Model Context Protocol (MCP) server, exposing your real Chrome browser—its tabs, login states, and config… | 50 | 12496 | active |
| simular-ai/Agent-S Agent S is an open-source agentic framework that uses multimodal LLMs to operate computers like a human, controlling GUIs via clicking, typ… | 67 | 12397 | active |
| TheR1D/shell_gpt ShellGPT (sgpt) is a Python command-line productivity tool that uses LLMs like GPT-4/5 or local models via Ollama to generate shell command… | 71 | 12291 | active |
| getomni-ai/zerox Zerox is a library (Node.js and Python packages) that performs OCR and document extraction by converting files like PDFs, DOCX, and images … | 32 | 12249 | active |
| FlagOpen/FlagEmbedding FlagEmbedding is the official Python toolkit for BAAI's BGE family of embedding models and rerankers, covering inference, evaluation, and f… | 82 | 12242 | active |
| gsd-build/get-shit-done A lightweight meta-prompting, context engineering, and spec-driven development system built as an extension for Claude Code. This repositor… | 10 | 64286 | maintenance |
| IDA Pro MCP An MCP server and IDA Pro plugin that connects IDA Pro's binary analysis capabilities to language models, enabling AI-assisted reverse engi… | 58 | 12214 | active |
| jina-ai/reader Jina AI Reader converts any URL into LLM-friendly markdown via the r.jina.ai prefix, and searches the web into markdown via s.jina.ai. It r… | 59 | 12158 | active |
| bytedance/trae-agent Trae Agent is an LLM-based CLI agent from ByteDance for general-purpose software engineering tasks, executing workflows via tools like file… | 45 | 12135 | active |
| LMCache/LMCache LMCache is a KV cache management layer for LLM inference that stores, compresses, and reuses KV caches across requests, sessions, and servi… | 88 | 12133 | active |
| google/sentencepiece SentencePiece is a fast, lightweight unsupervised text tokenizer and detokenizer for neural network-based text generation systems, implemen… | 83 | 12132 | stable |
| Bisheng BISHENG is an open-source LLM DevOps (LLMOps) platform for building enterprise AI applications, offering GenAI workflow orchestration, RAG,… | 92 | 12032 | active |
| tadata-org/fastapi_mcp FastAPI-MCP is a Python library that automatically exposes FastAPI endpoints as Model Context Protocol (MCP) tools, preserving request/resp… | 43 | 12012 | active |
| H2O h2oGPT is an Apache-2.0 open-source application for chatting with local, private LLMs and querying/summarizing your own documents (PDFs, Wo… | 10 | 11942 | active |
| jd-opensource/joyagent-jdgenie JoyAgent-JDGenie is an open-source, end-to-end, production-grade general-purpose multi-agent product built in Java. It directly answers use… | 36 | 11931 | active |
| Arize Phoenix Arize Phoenix is an open-source AI observability and evaluation platform for tracing, debugging, and evaluating LLM applications. It suppor… | 95 | 11875 | active |
| openchamber/openchamber OpenChamber is an open-source agentic development environment providing a visual workspace (desktop app, web/PWA, and VS Code extension) fo… | 81 | 11812 | active |
| ludwig-ai/ludwig Ludwig is a declarative, low-code deep learning framework for training, fine-tuning, and deploying AI models — from LLMs to tabular, image,… | 96 | 11775 | active |