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 |
|---|---|---|---|
| Lumiwealth/lumibot Lumibot is a Python framework for building, backtesting, and deploying algorithmic trading strategies and AI-agent trading teams across sto… | 96 | 2142 | active |
| btahir/open-deep-research An open-source web application that replicates Gemini's Deep Research by searching the web, extracting page content, and generating AI-writ… | 10 | 2142 | active |
| mcp-router/mcp-router MCP Router is a cross-platform desktop application for centrally managing Model Context Protocol (MCP) servers, with projects, workspaces, … | 10 | 2136 | active |
| anthropics/anthropic-sdk-typescript The official TypeScript/JavaScript SDK for accessing Anthropic's Claude language model APIs from server-side applications. It provides a ty… | 93 | 2132 | active |
| PKU-YuanGroup/LLaVA-CoT LLaVA-CoT is an 11B vision language model with training, inference, and dataset-generation code for spontaneous step-by-step multimodal rea… | 44 | 2131 | active |
| MemTensor/memmy-agent Memmy is a personal AI agent and local memory hub that gives every AI agent (Claude Code, Codex, Cursor, OpenClaw, etc.) a shared, locally … | 81 | 2129 | active |
| tairov/llama2.mojo A single-file implementation of Llama 2 transformer inference written in pure Mojo, leveraging SIMD and vectorization for fast CPU inferenc… | 71 | 2129 | active |
| zilliztech/GPTCache GPTCache is a Python library for building a semantic cache that stores and retrieves LLM responses based on embedding similarity, reducing … | 65 | 8209 | maintenance |
| google-gemini/genai-processors GenAI Processors is a lightweight Python library for building modular, asynchronous, and composable AI pipelines around Gemini and other ge… | 75 | 2122 | active |
| LC1332/Chat-Haruhi-Suzumiya An open-source role-playing chatbot project that revives anime characters like Haruhi Suzumiya using large language models, mimicking their… | 30 | 2120 | active |
| ModelEngine-Group/fit-framework FIT is an enterprise-grade AI development framework for the Java ecosystem, combining a polyglot function engine (Java/Python/C++), a strea… | 60 | 2117 | active |
| deepspeedai/DeepSpeed-MII DeepSpeed-MII is a Python library for high-throughput, low-latency large language model inference, built on DeepSpeed. It provides blocked … | 39 | 2114 | active |
| OpenAutoCoder/Agentless Agentless is a Python framework that automatically solves software development problems (bug fixing) using LLMs without an agent loop. It f… | 15 | 2114 | active |
| 0Chencc/clawgod ClawGod is a runtime patch applied on top of the official Claude Code CLI that unlocks hidden internal features, removes restrictions, and … | 81 | 2110 | active |
| KEV0143/Telegram-MedicalBot A Telegram-based user support system for medical inquiries that manages user questions through a ticket system. It generates suggested resp… | 40 | 2109 | active |
| itigges22/ATLAS ATLAS is a local-first coding agent that wraps compact open models with planning, candidate generation, quality scoring, sandboxed testing,… | 83 | 2106 | active |
| 4thfever/cultivation-world-simulator An open-source AI-driven Cultivation (Xianxia) world simulator where every cultivator NPC is an independent LLM-powered agent that observes… | 77 | 2106 | active |
| QwenLM/Qwen2-Audio Official repository for Qwen2-Audio, a 7B-parameter large audio-language model from Alibaba Cloud that accepts audio inputs and responds to… | 28 | 2104 | active |
| agentset-ai/agentset Agentset is an open-source RAG-as-a-service platform that handles document ingestion, chunking, embeddings, retrieval, and agentic search w… | 64 | 2103 | active |
| kimjammer/Neuro A local recreation of the Neuro-Sama AI VTuber that runs open-source LLMs on consumer hardware, combining realtime speech-to-text, text-to-… | 28 | 2101 | active |
| Open-Reasoner-Zero/Open-Reasoner-Zero Open-Reasoner-Zero is an open-source implementation of large-scale reinforcement learning training for reasoning-oriented language models, … | 28 | 2098 | active |
| maxritter/pilot-shell Pilot Shell is a framework that adds spec-driven planning, enforced TDD, persistent memory, and automatic quality gates to Claude Code and … | 81 | 2097 | active |
| midday-ai/ai-sdk-tools A monorepo of TypeScript utility packages extending the Vercel AI SDK, including multi-agent orchestration, Zustand-based chat state manage… | 41 | 2097 | active |
| bigcode-project/starcoder2 StarCoder2 is a family of open code generation language models (3B, 7B, 15B) trained on 600+ programming languages from The Stack v2, with … | 27 | 2095 | active |
| HRM-Text HRM-Text is a 1B-parameter text generation model based on the hierarchical recurrent HRM architecture, released with a complete pretraining… | 57 | 2093 | active |
| Mangi-11/Eta Eta is a third-party system-level AI agent for Android that uses Root and LSPosed to bypass app sandboxing, giving connected LLMs (BYOK: Ch… | 82 | 2091 | active |
| ex3ndr/llama-coder Llama Coder is a self-hosted GitHub Copilot replacement implemented as a VS Code extension. It uses Ollama running CodeLlama or Stable Code… | 27 | 2088 | active |
| boldsoftware/meat meat is a Go CLI tool that uses an LLM to abridge a code diff into a 'reading diff', reducing agent-written changes to the conceptually imp… | 53 | 2081 | active |
| Syngnat/GoNavi GoNavi is a native cross-platform desktop database client built with Wails (Go) and React, supporting 30+ data sources including PostgreSQL… | 79 | 2080 | active |
| stepfun-ai/Step-3.5-Flash Step 3.5 Flash is an open-source 196B-parameter sparse Mixture-of-Experts foundation model (11B active per token) from StepFun, focused on … | 46 | 2080 | active |
| voocel/ainovel-cli ainovel-cli is a Go-based CLI/TUI engine that turns a one-sentence premise into a complete long-form novel by coordinating three autonomous… | 79 | 2079 | active |
| NVIDIA-NeMo/RL NeMo RL is NVIDIA's open-source post-training library for scaling reinforcement learning methods (GRPO, PPO, DPO, SFT, distillation) on LLM… | 79 | 2077 | active |
| showlab/Code2Video Code2Video is a research framework from Show Lab (NUS) that generates educational videos by having multi-agent LLM pipelines write and rend… | 59 | 2076 | active |
| jd-opensource/OxyGent OxyGent is an open-source Python framework that unifies tools, models, and agents into modular 'Oxy' components for building multi-agent sy… | 57 | 2074 | active |
| ammaarreshi/Gemini-Search A Perplexity-style AI search engine web application powered by Google's Gemini 2.0 Flash model with Google Search grounding. It provides AI… | 21 | 2072 | active |
| lupantech/AgentFlow AgentFlow is a trainable, tool-integrated agentic framework that coordinates planner, executor, verifier, and generator modules through an … | 44 | 2064 | active |
| BoCloud/folib Folib is a self-hosted, all-language artifact repository manager supporting npm, Maven, PyPI, Docker, Go, Cargo, NuGet, Helm, and many othe… | 49 | 2063 | active |
| LangGraph4j LangGraph4j is a Java library for building stateful, multi-agent applications with LLMs, inspired by the Python LangGraph project. It lets … | 89 | 2060 | active |
| matrixorigin/matrixone MatrixOne is a cloud-native, distributed HTAP SQL database written in Go that is MySQL-compatible and includes built-in vector search and f… | 96 | 2057 | active |
| coder/xum Xum (formerly Mux) is an open-source desktop application for running multiple AI coding agents in parallel, each in its own isolated worksp… | 81 | 2057 | active |
| microsoft/foundry-dev-tools Microsoft Foundry Toolkit (formerly AI Toolkit) is a Visual Studio Code extension for building, testing, and deploying AI agents and models… | 81 | 2056 | active |
| zereight/gitlab-mcp A Model Context Protocol (MCP) server exposing GitLab APIs (projects, merge requests, issues, pipelines, wikis, releases, and more) to AI c… | 85 | 2053 | active |
| Nutlope/llamatutor LlamaTutor is an open-source AI personal tutor web application powered by Meta's Llama 3.1 70B model via Together AI inference. It is built… | 62 | 2051 | active |
| rebel0789/codexpro CodexPro is a local MCP server and CLI that connects a ChatGPT session to your machine and explicitly allowed repos, giving ChatGPT bounded… | 78 | 2045 | active |
| chatgpt.js A lightweight client-side JavaScript library (plus interactive CLI) for interacting with ChatGPT from the browser or Node.js. It provides a… | 10 | 2042 | active |
| Yi Yi is a family of open-source large language models trained from scratch by 01.AI, including base and chat models in multiple sizes, with b… | 28 | 7830 | maintenance |
| nottelabs/notte Notte is a full-stack framework and cloud platform for building, deploying, and scaling AI web agents and browser automations. It combines … | 85 | 2040 | active |
| noamgat/lm-format-enforcer A Python library that enforces output formats like JSON Schema or regex on language models by filtering allowed tokens at each generation s… | 60 | 2040 | active |
| QwenLM/Qwen3-Embedding Qwen3-Embedding is a series of text embedding and reranking models (0.6B, 4B, 8B) built on Qwen3 foundation models, with a Python repositor… | 35 | 2040 | active |
| Kochava-Studios/witsy Witsy is a cross-platform desktop AI assistant built with Electron and Vue 3 that lets users chat with many LLM providers using their own A… | 63 | 2038 | active |
| tensorflow/recommenders TensorFlow Recommenders is a Python library for building recommender system models on top of TensorFlow and Keras. It covers the full workf… | 84 | 2034 | active |
| grp06/openclaw-studio OpenClaw Studio is a web dashboard for managing OpenClaw agent gateways. It lets users connect to a Gateway over WebSocket, view and chat w… | 52 | 2034 | active |
| Doorman11991/smallcode SmallCode is a terminal-native AI coding agent optimized for small local LLMs (8B-35B parameters) running on consumer hardware. It compensa… | 70 | 2031 | active |
| hj01857655/kiro-account-manager A Tauri 2.x desktop application for centrally managing Kiro IDE accounts, with one-click account switching, quota monitoring, and token aut… | 76 | 2028 | active |
| CaviraOSS/PageLM PageLM is an open-source, AI-powered education platform inspired by NotebookLM that transforms study materials like PDFs and notes into int… | 62 | 2028 | active |
| ShellGPT ShellGPT is a free, multi-platform ChatGPT client supporting GPT-3.5, GPT-4, NewBing, and Claude without requiring an API key or login. It … | 37 | 2026 | active |
| open-compress/claw-compactor Claw Compactor is an open-source Python library and CLI tool that compresses LLM input tokens via a 14-stage Fusion Pipeline, achieving 15-… | 58 | 2024 | active |
| IBM/mcp-cli A Python command-line client for interacting with Model Context Protocol (MCP) servers, integrating LLMs via CHUK Tool Processor and CHUK-L… | 10 | 2024 | active |
| jimmc414/onefilellm OneFileLLM is a Python command-line tool and library that aggregates content from sources like GitHub repos, pull requests, arXiv/Sci-Hub p… | 66 | 2022 | active |
| memochou1993/gpt-ai-assistant GPT AI Assistant is an application that connects the OpenAI API with the LINE Messaging API, letting users chat with their own AI assistant… | 58 | 7742 | maintenance |
| Zoo-Code-Org/Zoo-Code Zoo Code is an open-source AI coding assistant delivered as a VS Code extension (with JetBrains/Open VSX support), continuing development o… | 82 | 2020 | active |
| supermemoryai/markdowner Markdowner is a fast web service that converts any website into LLM-ready markdown, with optional LLM filtering, detailed responses, and au… | 25 | 2019 | active |
| GuDaStudio/skills A collection of Anthropic Agent Skills for Claude Code that enable Claude to delegate coding tasks to other AI models such as OpenAI Codex … | 39 | 2018 | active |
| tatsu-lab/alpaca_eval AlpacaEval is an LLM-based automatic evaluation framework for instruction-following language models, producing win rates against a GPT-4 ba… | 33 | 2018 | active |
| HKUDS/MiniRAG MiniRAG is an extremely simple retrieval-augmented generation framework designed to work with small, open-source language models. It uses s… | 37 | 2017 | active |
| 64bit/async-openai async-openai is a Rust library providing typed, async clients for the OpenAI API, covering chat completions, responses, embeddings, assista… | 94 | 2016 | active |
| WuKongOpenSource/Wukong-AICRM Wukong AICRM is an open-source AI-powered CRM positioned as a Salesforce alternative, built in Java. It combines customer management, task … | 63 | 2015 | active |
| cambrian-mllm/cambrian Cambrian-1 is a fully open family of vision-centric multimodal large language models (MLLMs) from NYU's VISIONx group, with training and ev… | 43 | 2011 | active |
| deer-flow/llm-space LLM Space is a local-first desktop application for building, tracing, debugging, and evaluating LLM agents. It lets developers prototype ag… | 80 | 2010 | active |
| omnimind-ai/OmniBot OpenOmniBot (OmniBot) is an on-device AI agent app for Android, built with a native Kotlin host and Flutter UI, that runs a full understand… | 75 | 2010 | active |
| shcherbak-ai/contextgem ContextGem is an open-source Python LLM framework for extracting structured data and insights from documents with minimal code. It provides… | 90 | 2009 | active |
| doobidoo/mcp-memory-service A self-hosted persistent memory service for AI agents and Claude, exposing storage and semantic retrieval via REST API, MCP, OAuth, CLI, an… | 84 | 2007 | active |
| AgentOps-AI/tokencost A Python library that estimates the USD cost of LLM API calls by counting tokens for prompts and completions across 400+ models. It maintai… | 43 | 2007 | active |
| msoedov/agentic_security Agentic Security is an open-source LLM vulnerability scanner and AI red-teaming toolkit that probes large language models and agent workflo… | 83 | 2004 | active |
| vercel-labs/lat.md lat.md is a CLI tool that maintains a knowledge graph of your codebase as interconnected markdown files in a lat.md/ directory, with wiki l… | 77 | 2004 | active |
| gpt4free-ts A TypeScript replication of gpt4free that provides free access to GPT-4 and other LLM models by reverse-engineering various websites offeri… | 21 | 7666 | maintenance |
| GoogleCloudPlatform/scion Scion is a multi-agent orchestration platform that runs 'deep agents' like Claude Code and Gemini CLI in isolated containers, each with its… | 69 | 2003 | active |
| Niek/chatgpt-web A single-page web interface for OpenAI-compatible chat APIs, built with Svelte, where users bring their own API key and chats are stored pr… | 73 | 2001 | active |
| patterns-ai-core/langchainrb Langchain.rb is a Ruby library for building LLM-powered applications, providing a unified interface to many LLM providers (OpenAI, Anthropi… | 73 | 2001 | active |
| zai-org/GLM-130B GLM-130B is an open bilingual (English and Chinese) 130-billion-parameter dense language model pre-trained with the General Language Model … | 32 | 7650 | maintenance |
| zouyuxuan122/Deepseek-Harness-EAC Deepseek Harness EAC is a Windows (and macOS) desktop client that wraps the official DeepSeek agent harness CLI (@deepseek-ai/dsh) into a o… | 80 | 2000 | active |
| GuDaStudio/codexmcp CodexMCP is an MCP server that bridges Claude Code and OpenAI Codex CLI, letting the two AI coding agents collaborate with each other. It a… | 42 | 2000 | active |
| win4r/AISuperDomain Aila (AISuperDomain) is a cross-platform desktop application that lets users send one prompt to 10+ AI chat services (ChatGPT, Gemini, Clau… | 60 | 1999 | active |
| Strix Halo AI Toolboxes A collection of pre-built Toolbx/Docker containers ('toolboxes') for running llama.cpp LLM inference on AMD Ryzen AI Max 'Strix Halo' integ… | 64 | 1998 | active |
| lucidrains/titans-pytorch An unofficial PyTorch implementation of the Titans architecture, a neural long-term memory module for transformers that learns to memorize … | 64 | 1996 | active |
| glebkudr/shotgun_code Shotgun is a desktop application that packages a local codebase into a structured context payload for LLMs, with AI-powered file selection … | 46 | 1995 | active |
| j4wg/interview-coder-withoupaywall-opensource A free, open-source desktop application (CodeInterviewAssist) that provides AI-powered coding interview assistance, including problem analy… | 34 | 1994 | active |
| tsingyuai/growth-lab Growth Lab is an open-source, end-to-end AI growth system that runs product marketing and user-acquisition loops through natural-language c… | 57 | 1991 | active |
| openakita/openakita OpenAkita is an open-source multi-agent AI assistant framework in Python that orchestrates multiple cooperating agents with skills, plugins… | 76 | 1990 | active |
| haykgrigo3/TimeCapsuleLLM TimeCapsuleLLM is a research project training language models from scratch (and fine-tuning small base models) exclusively on text from spe… | 70 | 1989 | active |
| nhaouari/obsidian-textgenerator-plugin An open-source Obsidian plugin that brings generative AI text generation into the note-taking workflow, supporting providers like OpenAI, A… | 86 | 1988 | active |
| GPT2-Chinese A Python library providing GPT-2 training and text generation code tailored for Chinese, built on HuggingFace Transformers with BERT or BPE… | 32 | 7594 | maintenance |
| filiksyos/gitreverse GitReverse is a web application that turns any public GitHub repository into a single synthetic prompt that could have been used to vibe-co… | 60 | 1984 | active |
| forloopcodes/contextplus Context+ is an MCP server that gives AI coding agents semantic understanding of large codebases by combining RAG embeddings, Tree-sitter AS… | 53 | 1983 | active |
| mudler/LocalAGI LocalAGI is a self-hostable, privacy-focused AI agent platform written in Go that lets users create no-code agents, automations, and chatbo… | 85 | 1979 | active |
| 2U1/Qwen-VL-Series-Finetune An open-source Python repository providing training scripts for fine-tuning Alibaba's Qwen-VL series of vision-language models (Qwen2-VL, Q… | 65 | 1977 | active |
| helallao/perplexity-ai An unofficial Python wrapper for Perplexity.ai that reverse-engineers the web interface, supporting sync and async APIs, streaming response… | 74 | 1976 | active |
| run-llama/notebookllama NotebookLlaMa is an open-source, Python-based alternative to Google's NotebookLM, backed by LlamaCloud for document ingestion and retrieval… | 49 | 1976 | active |
| firecrawl/fireplexity Fireplexity is an open-source, Perplexity-style AI search engine built with TypeScript that delivers answers with real-time citations, stre… | 33 | 1975 | active |
| OpenMotionLab/MotionGPT MotionGPT is a unified motion-language model that treats 3D human motion as a foreign language by converting motion into discrete motion to… | 30 | 1974 | active |