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 |
|---|---|---|---|
| microsoft/graphrag GraphRAG is a Python library and CLI pipeline from Microsoft Research that extracts a knowledge graph from unstructured text, builds commun… | 92 | 36292 | maintenance |
| open-compass/opencompass OpenCompass is a Python-based evaluation platform and toolkit for benchmarking large language models across 100+ datasets, supporting model… | 93 | 7471 | active |
| EleutherAI/gpt-neox GPT-NeoX is EleutherAI's library for training large-scale autoregressive transformer language models on GPUs, built on NVIDIA's Megatron an… | 67 | 7471 | active |
| TheCraigHewitt/seomachine SEO Machine is a specialized Claude Code workspace of custom commands, AI agents, and Python analysis modules for researching, writing, and… | 57 | 7467 | active |
| traceloop/openllmetry OpenLLMetry is an open-source set of OpenTelemetry extensions and SDKs that provide observability (tracing, metrics, logging) for LLM and G… | 90 | 7463 | active |
| Agent-Native Agent-Native is an open-source TypeScript framework for building applications that serve both human users and AI agents from a single codeb… | 79 | 7463 | active |
| LargeWorldModel/LWM Large World Model (LWM) is a family of open-source 7B-parameter multimodal autoregressive transformer models trained on long videos and boo… | 26 | 7425 | active |
| MuiseDestiny/zotero-gpt A Zotero plugin that integrates OpenAI GPT models into the Zotero reference manager, letting users ask questions about PDFs, summarize pape… | 73 | 7420 | active |
| spinabot/brigade Brigade is a self-hosted, MIT-licensed multi-agent runtime where a crew of AI agents on an org chart delegate work, switch models mid-task,… | 73 | 7412 | active |
| Gentle-AI Engram is a persistent memory system for AI coding agents, shipped as a single agent-agnostic Go binary backed by SQLite with FTS5 full-tex… | 79 | 7403 | active |
| arcee-ai/mergekit mergekit is a Python toolkit for merging pre-trained large language models directly in weight space, supporting many merge methods (SLERP, … | 64 | 7389 | active |
| zai-org/GLM-5 GLM-5 is a family of open-weight large language models from Z.ai (Zhipu AI), including the flagship GLM-5.2 with 1M-token context and the m… | 60 | 7329 | active |
| Honcho Honcho is an open-source memory infrastructure service for building stateful AI agents that maintain understanding of users, agents, groups… | 82 | 7327 | active |
| Nasiko-Labs/nasiko Nasiko is a developer control plane for AI agents, built in Rust, that lets teams deploy, route, secure, and observe A2A-speaking agents wi… | 57 | 7324 | active |
| interviewstreet/hiring-agent An open-source AI agent pipeline from HackerRank that extracts structured data from resume PDFs, enriches it with GitHub signals, and produ… | 63 | 7312 | active |
| kyegomez/swarms Swarms is an enterprise-grade Python framework for orchestrating multi-agent systems powered by large language models, offering prebuilt se… | 66 | 7282 | active |
| vLLM vLLM-Omni is a Python framework extending vLLM for efficient inference and serving of omni-modality models, including diffusion transformer… | 84 | 7280 | active |
| InternLM/InternLM Official repository for the InternLM series of open-source large language models (InternLM, InternLM2, InternLM2.5, InternLM3), including p… | 38 | 7276 | active |
| Zipstack/unstract Unstract is an open-source, LLM-driven platform that extracts structured JSON data from unstructured documents such as PDFs, images, and sc… | 87 | 7270 | active |
| mit-han-lab/streaming-llm StreamingLLM is a research framework from MIT Han Lab implementing the Attention Sinks method (ICLR 2024) for efficient streaming language … | 28 | 7267 | stable |
| ml-explore/mlx-lm A Python package for running and fine-tuning large language models on Apple silicon using the MLX framework. It integrates with the Hugging… | 78 | 7259 | active |
| xerrors/Yuxi Yuxi is a self-hosted, multi-tenant knowledge agent platform that unifies RAG, knowledge graph construction (Milvus + Neo4j), LangGraph mul… | 84 | 7256 | active |
| magnitudedev/magnitude Magnitude is an open-source CLI tool and agent that bundles local LLM inference with an agent harness, profiling your hardware to recommend… | 82 | 7240 | active |
| craft-ai-agents/craft-agents-oss Craft Agents is an open-source, agent-native desktop application for working with AI agents in a document-centric, GUI-based workflow inste… | 78 | 7240 | active |
| AI Scientist An end-to-end autonomous AI research system that generates hypotheses, runs machine learning experiments, analyzes data, and writes complet… | 43 | 7222 | active |
| MineDojo/Voyager Voyager is an open-source LLM-powered embodied agent that plays Minecraft through GPT-4, using an automatic curriculum, an ever-growing ski… | 30 | 7219 | active |
| deepseek-ai/DeepSpec DeepSpec is a full-stack Python codebase from DeepSeek for training and evaluating draft models used in speculative decoding of large langu… | 51 | 7207 | active |
| Lance Lance is an open lakehouse data format (file format, table format, and catalog spec) for multimodal AI, implemented in Rust with Python and… | 95 | 7182 | active |
| NVIDIA-NeMo/Guardrails NVIDIA NeMo Guardrails is an open-source Python toolkit for adding programmable guardrails to LLM-based conversational applications. It sit… | 90 | 7181 | active |
| flwrlabs/flower Flower (flwr) is an open-source Python framework for building federated and collaborative AI systems, supporting any ML framework such as P… | 99 | 7162 | active |
| tbphp/gpt-load GPT-Load is a high-performance, enterprise-grade AI API transparent proxy service built in Go that aggregates multiple AI providers (OpenAI… | 83 | 7158 | active |
| Automaton Automaton is a TypeScript runtime for continuously running, self-improving AI agents that pay for their own compute via an Ethereum wallet … | 67 | 7156 | active |
| dwzhu-pku/PaperBanana PaperBanana is a reference-driven multi-agent framework that automatically generates publication-ready academic illustrations such as metho… | 52 | 7150 | active |
| enricoros/big-AGI Big-AGI is an open-source AI workspace web application that lets users chat with many state-of-the-art LLM providers (OpenAI, Anthropic, Ge… | 91 | 7147 | active |
| OpenAI Codex Plugins A catalog of Agent Skills—folders of instructions, scripts, and resources—for OpenAI's Codex CLI agent, distributed via the openai/skills a… | 58 | 7137 | active |
| datajuicer/data-juicer Data-Juicer is a Python library and data processing system for cleaning, deduplicating, synthesizing, and analyzing data for foundation mod… | 94 | 7132 | active |
| Nutlope/llamacoder Llama Coder is an open-source web application that generates small apps from a single prompt, similar to Claude Artifacts, powered by Llama… | 67 | 7130 | active |
| Vespa Vespa is an open-source, distributed AI search platform and serving engine that combines full-text search, vector/tensor search, and machin… | 93 | 7117 | stable |
| ymcui/Chinese-LLaMA-Alpaca-2 A project releasing Chinese-adapted LLaMA-2 base models and Alpaca-2 instruction-tuned chat models with an extended Chinese vocabulary, inc… | 51 | 7112 | stable |
| chenfei-wu/TaskMatrix TaskMatrix (Visual ChatGPT) is a Python framework that connects ChatGPT with a suite of visual foundation models like Stable Diffusion, Gro… | 31 | 33957 | maintenance |
| agegr/pi-web Pi Web is a local browser-based UI for the pi coding agent, sharing its configuration and session files. It lets users browse and resume ag… | 81 | 7093 | active |
| katanemo/plano Plano is an AI-native proxy server and data plane for agentic applications, built on Envoy by its core contributors. It centralizes agent r… | 86 | 7092 | active |
| albertan017/LLM4Decompile LLM4Decompile is an open-source series of large language models (1.3B to 33B) trained to decompile binary code back into readable, executab… | 53 | 7076 | active |
| opensquilla/opensquilla OpenSquilla is a token-efficient, microkernel AI agent that routes each conversation turn to the cheapest capable LLM via a local model rou… | 80 | 7069 | active |
| zai-org/GLM-4 Official repository for the GLM-4 series of open-weight, multilingual (primarily Chinese/English) multimodal chat language models from Z.ai… | 64 | 7069 | active |
| google/gemma.cpp A lightweight, standalone C++ inference engine for Google's Gemma foundation models (Gemma 2/3, PaliGemma 2), with a small ~2K LoC core and… | 73 | 7060 | active |
| grab/cursor-talk-to-figma-mcp An MCP server plus Figma plugin that lets AI agents like Cursor, Claude Code, and Codex read and programmatically modify Figma designs. A W… | 59 | 7054 | active |
| TheTom/turboquant_plus TurboQuant+ is a Python reference implementation of the TurboQuant KV cache compression method (ICLR 2026), using PolarQuant codebooks and … | 54 | 7036 | active |
| deepseek-ai/DeepSeek-Coder-V2 DeepSeek-Coder-V2 is an open-weight Mixture-of-Experts code language model family released by DeepSeek AI, with weights available on Huggin… | 44 | 7012 | active |
| SuanmoSuanyangTechnology/MemoryBear MemoryBear is an AI memory management system that gives LLM agents and chatbots human-like long-term memory across a full lifecycle of perc… | 83 | 7009 | active |
| dsh-routing-suite A bundled kit for the DSH (DeepSeek harness) agent runtime combining a runtime injector plugin with task-aware reasoning-mode router preset… | 76 | 6999 | active |
| gepa-ai/gepa GEPA is a Python framework that optimizes textual system parameters such as prompts, code, and agent configurations using LLM-based reflect… | 81 | 6996 | active |
| mckaywrigley/chatbot-ui Chatbot UI is an open-source, self-hostable web chat application for conversing with any AI model, with chat history and multi-model suppor… | 31 | 33349 | maintenance |
| openai/openai-realtime-agents A Next.js TypeScript demo application showcasing advanced agentic patterns (Chat-Supervisor and Sequential Handoff) built on the OpenAI Rea… | 45 | 6989 | active |
| open-multi-agent/open-multi-agent Open Multi-Agent (OMA) is an MIT-licensed TypeScript framework for multi-agent AI orchestration that runs inside Node.js backends. A coordi… | 81 | 6974 | active |
| InternLM/MindSearch MindSearch is an open-source, LLM-based multi-agent framework that mimics human cognition to perform deep web searches, similar to Perplexi… | 24 | 6943 | active |
| mishushakov/llm-scraper A TypeScript library that turns any webpage into structured data using LLMs, built on Playwright and the Vercel AI SDK. It supports multipl… | 68 | 6937 | active |
| yihong0618/xiaogpt A Python application that connects Xiaomi AI Speakers to ChatGPT and other LLMs, letting users ask questions starting with a trigger phrase… | 58 | 6921 | active |
| Tencent/AI-Infra-Guard Tencent's full-stack AI red teaming platform that scans AI infrastructure, agents, MCP servers, and skills for vulnerabilities and evaluate… | 85 | 6916 | active |
| adbar/trafilatura Trafilatura is a Python package and command-line tool for crawling the web and extracting main text, metadata, and comments from raw HTML w… | 94 | 6914 | active |
| ClearML ClearML is an open-source Python SDK and platform for MLOps/LLMOps that provides auto-logged experiment tracking, data versioning, pipeline… | 96 | 6903 | stable |
| TencentQQGYLab/AppAgent AppAgent is an LLM-based multimodal agent framework that operates smartphone apps through human-like interactions such as tapping and swipi… | 29 | 6896 | active |
| SenseNova SenseNova-U is a series of open-weight unified multimodal models (e.g., SenseNova-U1.5-8B-MoT) built on the NEO-unify architecture that com… | 58 | 6884 | active |
| dataease/SQLBot SQLBot is an open-source conversational data analysis (ChatBI) system that converts natural language questions into SQL queries using large… | 86 | 6880 | active |
| drumih/turbo-fieldfare TurboFieldfare is a custom Swift + Metal runtime that runs Gemma 4 26B-A4B inference in roughly 2 GB of RAM on Apple Silicon Macs by stream… | 79 | 6880 | active |
| olimorris/codecompanion.nvim CodeCompanion.nvim is a Neovim plugin that integrates LLMs (Anthropic, OpenAI, Gemini, Copilot, Ollama, and more) and CLI coding agents (Cl… | 87 | 6872 | active |
| iPolloWork iPolloWork is an enterprise-grade, local-first agent workbench that unifies multiple agent engines (Codex Harness, DeepSeek Harness, OpenCo… | 84 | 6866 | active |
| kvcache-ai/Mooncake Mooncake is a KVCache-centric disaggregated serving platform for LLM inference, originally built to serve Kimi by Moonshot AI. It separates… | 90 | 6835 | active |
| zarazhangrui/follow-builders An AI agent skill that tracks top AI builders on X/Twitter, YouTube podcasts, and AI company blogs, then remixes their content into digesti… | 59 | 6828 | active |
| stagewise-io/stagewise Stagewise is an open-source agentic IDE with a built-in coding agent that can see live app context, run git workflows, and orchestrate mult… | 80 | 6823 | active |
| postgresml/postgresml PostgresML is a PostgreSQL extension that brings machine learning and AI inference directly into the database, with GPU acceleration and pg… | 32 | 6823 | active |
| liliMozi/openhanako HanaAgent is a cross-platform desktop application providing a personal AI agent with persistent memory, customizable personality, and auton… | 76 | 6809 | active |
| Dooy/chatgpt-web-midjourney-proxy A unified web/desktop UI for ChatGPT plus AI image, music, and video generation services like Midjourney, Suno, Luma, Runway, and Flux. It … | 93 | 6795 | active |
| zhukunpenglinyutong/jetbrains-cc-gui A JetBrains IntelliJ IDEA plugin providing a visual GUI for Claude Code and OpenAI Codex AI coding assistants. It adds conversation, agent,… | 82 | 6776 | active |
| superagent-ai/superagent Superagent is an open-source SDK and platform for securing AI applications and agents, offering runtime guardrails that block prompt inject… | 73 | 6759 | active |
| flashinfer-ai/flashinfer FlashInfer is a GPU kernel library and kernel generator for LLM inference, providing unified APIs for attention, GEMM, and MoE operations w… | 92 | 6728 | active |
| Andyyyy64/whichllm whichllm is a Python CLI tool that auto-detects your GPU, CPU, and RAM, then ranks local LLMs from HuggingFace that will actually run and p… | 82 | 6724 | active |
| langchain-ai/opengpts OpenGPTs is an open-source platform for building and hosting custom AI assistants similar to OpenAI's GPTs and Assistants API. It is built … | 10 | 6707 | active |
| google-ai-edge/LiteRT-LM LiteRT-LM is Google's production-ready, high-performance open-source framework for running large language models on edge devices, built as … | 88 | 6702 | active |
| 11cafe/jaaz Jaaz is an open-source multimodal creative assistant application that serves as a privacy-focused, locally usable alternative to Canva and … | 49 | 6689 | active |
| microsoft/LLMLingua LLMLingua is a Microsoft library for prompt compression that removes non-essential tokens from prompts and KV caches to speed up LLM infere… | 62 | 6687 | active |
| simplescaling/s1 s1 is an open-source research project implementing simple test-time scaling for large language models, including the s1K dataset of 1,000 c… | 30 | 6675 | active |
| lharries/whatsapp-mcp A Model Context Protocol (MCP) server that connects an LLM agent like Claude Desktop or Cursor to a personal WhatsApp account via the Whats… | 21 | 6666 | active |
| linkedin/Liger-Kernel Liger Kernel is a collection of Triton kernels designed to make LLM training faster and more memory-efficient, offering drop-in replacement… | 91 | 6664 | active |
| outsourc-e/hermes-workspace Hermes Workspace is a native web UI for the Nous Research Hermes Agent, bundling chat, terminal, memory browsing, skills marketplace, MCP m… | 72 | 6661 | active |
| yangjianxin1/Firefly Firefly is an open-source one-stop training tool for large language models, supporting pretraining, instruction fine-tuning (SFT), and DPO … | 21 | 6653 | active |
| Chanzhaoyu/chatgpt-web A self-hosted ChatGPT demo web application built with Express (Node.js backend) and Vue 3 frontend. It supports two access methods: the off… | 10 | 31414 | maintenance |
| ultraworkers/claw-code-parity A temporary Rust workspace tracking parity work for the claw-code coding agent while the original repo undergoes migration to Rust. It prov… | 10 | 6624 | active |
| BlockRunAI/ClawRouter ClawRouter is an open-source TypeScript LLM router built for autonomous AI agents, offering 71 models from OpenAI, Anthropic, Google, xAI, … | 79 | 6621 | active |
| julep-ai/julep Julep is an open-source framework and platform for building durable, composable AI agents as dataflows that can crash, resume, retry, and e… | 65 | 6576 | active |
| souzatharsis/podcastfy Podcastfy is an open-source Python package and CLI that transforms multimodal content (websites, PDFs, images, YouTube videos, topics) into… | 57 | 6576 | active |
| openai/openai-cs-agents-demo A demo application from OpenAI implementing a customer service chat experience using the OpenAI Agents SDK, with a Python backend for multi… | 41 | 6575 | active |
| microsoft/call-center-ai An AI-powered call center service that lets you initiate or receive phone calls handled by an LLM-driven agent via a simple API call. Built… | 65 | 6570 | active |
| airweave-ai/airweave Airweave is an open-source context retrieval layer that connects to apps, databases, and documents and exposes their data through a single … | 10 | 6558 | active |
| basketikun/chatgpt2api A self-hosted reverse-engineered implementation of ChatGPT's official web interfaces, exposing OpenAI-compatible API endpoints for text gen… | 71 | 6544 | active |
| shibing624/pycorrector pycorrector is a Python toolkit for Chinese text error correction, supporting phonetic, visual, and grammar error types with models includi… | 78 | 6528 | active |
| Genkit Genkit is an open-source framework by Google for building full-stack, AI-powered agentic applications in JavaScript/TypeScript, Go, Python,… | 87 | 6524 | stable |
| crestalnetwork/intentkit IntentKit is an open-source, self-hosted cloud-native agent cluster that runs and manages a collaborative team of AI agents as containerize… | 76 | 6516 | active |
| josStorer/RWKV-Runner RWKV-Runner is a lightweight desktop application that automates downloading, managing, and running RWKV large language models with a GUI. I… | 85 | 6486 | active |
| CodePilot CodePilot is a multi-model AI agent desktop client built with Electron and Next.js that connects to 17+ AI providers through a single inter… | 76 | 6471 | active |