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 |
|---|---|---|---|
| biobootloader/wolverine Wolverine is a Python CLI tool that runs Python scripts and, when they crash, sends the error to GPT-4 which edits the file and reruns it r… | 31 | 5060 | abandoned |
| TheoKanning/openai-java A Java client library for the OpenAI API, providing POJOs, a Retrofit-based client, and a convenience service class for GPT-3, ChatGPT, and… | 10 | 4719 | abandoned |
| huggingface/autotrain-advanced AutoTrain Advanced is Hugging Face's no-code tool for training and deploying state-of-the-art machine learning models, covering LLM finetun… | 76 | 4612 | abandoned |
| truefoundry/cognita Cognita is an open-source RAG (Retrieval Augmented Generation) framework by TrueFoundry for building modular, production-ready RAG applicat… | 10 | 4420 | abandoned |
| amazon-archives/amazon-dsstne DSSTNE (Deep Scalable Sparse Tensor Network Engine) is a C++ GPU library from Amazon for training and deploying deep learning recommendatio… | 10 | 4390 | abandoned |
| chatpire/chatgpt-web-share A self-hosted web application for sharing a single ChatGPT Plus account among multiple users, with conversation isolation, usage quotas, an… | 22 | 4275 | abandoned |
| rawandahmad698/PyChatGPT PyChatGPT is a Python client and CLI for ChatGPT that reverse-engineers the ChatGPT web interface, handling automatic login, access token r… | 70 | 4185 | abandoned |
| waylaidwanderer/node-chatgpt-api A Node.js client implementation for ChatGPT and Bing AI, usable as an npm module, a REST API server, or a CLI app. It wraps the official Op… | 22 | 4152 | abandoned |
| karpathy/reader3 A lightweight, self-hosted EPUB reader web app that presents books one chapter at a time so users can easily copy text into an LLM and read… | 37 | 3877 | abandoned |
| WhatsApp ChatGPT AI Assistant A self-hosted WhatsApp bot that connects OpenAI's GPT and DALL-E 2 to WhatsApp, letting users chat with an AI assistant and generate images… | 70 | 3786 | abandoned |
| ravenscroftj/turbopilot TurboPilot is a self-hosted, Copilot-like code completion server that runs large language models (Salesforce CodeGen, StableCode, WizardCod… | 10 | 3772 | abandoned |
| facebookresearch/ReAgent ReAgent is an open-source end-to-end platform for applied reinforcement learning developed at Facebook, built in Python with PyTorch for tr… | 74 | 3722 | abandoned |
| hiyouga/ChatGLM-Efficient-Tuning A Python framework for parameter-efficient fine-tuning (LoRA, QLoRA, P-Tuning, RLHF) of the ChatGLM-6B and ChatGLM2-6B language models usin… | 10 | 3710 | abandoned |
| twinnydotdev/twinny Twinny is a free, MIT-licensed Visual Studio Code extension providing AI code completion (fill-in-the-middle) and code chat, working with l… | 94 | 3659 | abandoned |
| mukulpatnaik/researchgpt A FastAPI-based research assistant that lets users have a conversation with any PDF research paper by extracting text, generating embedding… | 10 | 3527 | abandoned |
| gencay/vscode-chatgpt An unofficial Visual Studio Code extension integrating OpenAI ChatGPT, providing sidebar conversations, streaming answers, and code inserti… | 23 | 3448 | abandoned |
| ayaka14732/ChatGPTAPIFree An open-source proxy API that lets users access OpenAI's ChatGPT API for free, with rate limiting and self-hosting support. The repository … | 10 | 3322 | abandoned |
| protectai/llm-guard LLM Guard is a Python library providing input and output scanners to secure LLM interactions, including sanitization, harmful language dete… | 10 | 3208 | abandoned |
| alpa-projects/alpa Alpa is a Python system for training and serving large-scale neural networks by automatically parallelizing single-device code across distr… | 10 | 3176 | abandoned |
| neuralmagic/deepsparse DeepSparse is a sparsity-aware deep learning inference runtime that delivers GPU-class performance on x86 CPUs for ONNX models, covering co… | 10 | 3157 | abandoned |
| Mintlify Documentation Mintlify Writer is an AI-powered editor plugin (VS Code extension and IntelliJ plugin) that generates docstrings and documentation from hig… | 10 | 3127 | abandoned |
| NVIDIA/ChatRTX ChatRTX is a Windows demo application for building personalized RAG chatbots on local RTX GPUs using TensorRT-LLM, NVIDIA NIM, and LlamaInd… | 10 | 3116 | abandoned |
| mistralai/mistral-finetune A lightweight Python codebase from Mistral AI for memory-efficient LoRA fine-tuning of Mistral's language models, optimized for single-node… | 10 | 3094 | abandoned |
| gragland/chatgpt-chrome-extension A Chrome extension that integrates ChatGPT into every text box on the internet, letting users invoke AI assistance via right-click without … | 32 | 2961 | abandoned |
| janhq/cortex.cpp Cortex.cpp is a C++ local AI platform that runs GGUF (llama.cpp) and ONNX models on your own machine, exposing an OpenAI-compatible HTTP AP… | 10 | 2748 | abandoned |
| npiv/chatblade Chatblade is a Python CLI tool for querying OpenAI's ChatGPT from the terminal, supporting piped input, saved prompt preambles, session rec… | 47 | 2590 | abandoned |
| ading2210/poe-api A reverse-engineered Python API wrapper for Quora's Poe, providing programmatic access to ChatGPT, GPT-4, and Claude via Poe's web interfac… | 10 | 2462 | abandoned |
| Azure-Samples/graphrag-accelerator A one-click Azure deployment accelerator that hosts the GraphRAG knowledge-graph-powered RAG system as a scalable API service. It builds on… | 10 | 2406 | abandoned |
| AutoAWQ AutoAWQ is a Python library implementing the Activation-aware Weight Quantization (AWQ) algorithm for 4-bit quantization of large language … | 10 | 2346 | abandoned |
| google-gemini/deprecated-generative-ai-python The deprecated Google AI Python SDK for the Gemini API, which allowed developers to integrate Google's generative AI models into Python app… | 10 | 2326 | abandoned |
| instill-ai/instill-core Instill Core is a full-stack AI infrastructure tool for data, model, and pipeline orchestration, aimed at building AI-first applications wi… | 70 | 2317 | abandoned |
| openai/finetune-transformer-lm Reference code and model for OpenAI's paper 'Improving Language Understanding by Generative Pre-Training' (the original GPT-1), implemented… | 10 | 2307 | abandoned |
| microsoft/kernel-memory Kernel Memory is a multi-modal AI service and .NET library for indexing datasets through hybrid data pipelines, enabling RAG, semantic sear… | 66 | 2233 | abandoned |
| hncboy/ai-beehive AI Beehive is a self-hosted Java web application (Spring Boot 3, JDK 17) that provides modular chat rooms for interacting with multiple AI … | 52 | 2210 | abandoned |
| Aide Aide is an open-source, AI-native code editor built as a fork of VS Code, integrating agentic AI for chat-driven multi-file edits, proactiv… | 10 | 2192 | abandoned |
| run-llama/llama_deploy LlamaDeploy is a Python framework for deploying LlamaIndex agentic workflows to production, with support for multi-agent services. The proj… | 67 | 2068 | abandoned |
| lxe/simple-llm-finetuner A beginner-friendly Gradio web UI for fine-tuning LLMs (LLaMA, GPT-2) using LoRA via the Hugging Face PEFT library on consumer NVIDIA GPUs.… | 31 | 2052 | abandoned |
| intel/intel-extension-for-pytorch A Python package extending official PyTorch with Intel-specific optimizations for CPUs and GPUs, including quantization and LLM inference a… | 10 | 2012 | abandoned |
| BCG-X-Official/agentkit AgentKit is a full-stack starter kit from BCG X for building constrained, chat-based LLM agent applications using Next.js/React on the fron… | 10 | 1943 | abandoned |
| langchain-ai/open-agent-platform Open Agent Platform is an open-source, no-code web platform for building, configuring, and managing LangGraph agents with RAG integration, … | 10 | 1897 | abandoned |
| Pythagora-io/pythagora Pythagora is an npm CLI tool (with a VS Code extension) that uses LLMs like GPT-4 to automatically generate unit and integration tests for … | 67 | 1823 | abandoned |
| n4ze3m/dialoqbase Dialoqbase is an open-source self-hosted application for creating custom chatbots powered by a personal knowledge base, supporting many cha… | 10 | 1791 | abandoned |
| IntelLabs/fastRAG fastRAG is a Python research framework for building efficient, optimized retrieval-augmented generation (RAG) pipelines, built on Haystack … | 10 | 1786 | abandoned |
| AutoForgeAI/autoforge AutoForge is a long-running autonomous coding agent built on the Claude Agent SDK that builds complete applications across multiple session… | 54 | 1772 | abandoned |
| Onju Voice A hackable AI home assistant platform that replaces the internals of a Google Nest Mini with a custom ESP32-S3 PCB, paired with a server th… | 60 | 1732 | abandoned |
| 0x676e67/ninja Ninja is a reverse-engineered ChatGPT proxy server written in Rust that proxies ChatGPT-API/OpenAI-API requests, handles account authentica… | 10 | 1677 | abandoned |
| Veloera/Veloera Veloera is a self-hosted AI API gateway written in Go, forked from New API, that proxies and manages access to multiple LLM providers with … | 49 | 1634 | abandoned |
| jina-ai/langchain-serve langchain-serve is a Python framework for deploying LangChain applications to production using Jina and FastAPI, exposing them as REST/Webs… | 10 | 1634 | abandoned |
| openai/sparse_attention A Python library of sparse attention primitives from OpenAI's Sparse Transformers paper, including fused normal attention and strided/fixed… | 10 | 1612 | abandoned |
| MeetKai/functionary Functionary is a chat language model and serving code that interprets and executes functions/plugins, deciding when to call tools in parall… | 66 | 1593 | abandoned |
| mark3labs/mcphost MCPHost is a Go CLI host application that lets LLMs (Claude, OpenAI, Gemini, Ollama, and OpenAI-compatible endpoints) interact with externa… | 10 | 1592 | abandoned |
| Farama-Foundation/ChatArena ChatArena is a Python library providing multi-agent language game environments for large language models, built around a Markov Decision Pr… | 34 | 1567 | abandoned |
| huggingface/pytorch-openai-transformer-lm A PyTorch reimplementation of OpenAI's finetuned transformer language model (GPT-1) from the paper 'Improving Language Understanding by Gen… | 10 | 1525 | abandoned |
| thecookingsenpai/autogpt-gui A graphical user interface for AutoGPT built with JavaScript and Node.js, allowing users to interact with AutoGPT agents through a visual i… | 10 | 1499 | abandoned |
| KnowledgeCanvas/knowledge Knowledge is a desktop application for saving, searching, exploring, and chatting with websites, documents, and files using a knowledge gra… | 76 | 1462 | abandoned |
| SmartSchoolAI/ai-to-pptx Ai-to-pptx is an open-source web application (Vue frontend plus PHP backend) that uses large language models like DeepSeek to generate pres… | 52 | 1460 | abandoned |
| idootop/migpt-next MiGPT-Next is a TypeScript library and Docker-runnable service that connects Xiaomi's XiaoAI smart speakers to OpenAI-compatible large lang… | 10 | 1445 | abandoned |
| anaclumos/bing-chat-for-all-browsers A browser extension that enables Bing Chat (Microsoft's ChatGPT-powered search assistant) on Chrome and Firefox, which normally restrict it… | 10 | 1423 | abandoned |
| dairoot/ChatGPT-Mirror A self-hosted ChatGPT mirror site that lets multiple users share ChatGPT accounts through a managed web interface with an admin backend. It… | 53 | 1404 | abandoned |
| acheong08/Bard A Python SDK and CLI that reverse engineers Google's Bard chatbot API, allowing programmatic access using session cookies. It offers both s… | 10 | 1391 | abandoned |
| openai/lm-human-preferences OpenAI's research code for the paper 'Fine-Tuning Language Models from Human Preferences', implementing reward model training from human la… | 10 | 1388 | abandoned |
| prefect-archive/ControlFlow ControlFlow is a Python framework for building agentic AI workflows, letting developers define discrete observable tasks, assign specialize… | 10 | 1387 | abandoned |
| regenrek/deepwiki-mcp An unofficial MCP server that fetches deepwiki.com documentation, crawls its pages, converts them to Markdown, and serves them to MCP-compa… | 49 | 1386 | abandoned |
| ChatGPT API Bypass A Go service that bypasses Cloudflare protection to access ChatGPT's unofficial web endpoints, exposing them as an HTTP API. It also offers… | 10 | 1380 | abandoned |
| irgolic/AutoPR AutoPR is a GitHub Action that autonomously generated pull requests in response to issues, planning a fix, writing code, pushing a branch, … | 10 | 1373 | abandoned |
| cfrs2005/claude-init A Chinese-localized project initialization toolkit for Claude Code that sets up an AI coding environment with MCP servers, agents, skills, … | 55 | 1359 | abandoned |
| Atropos Atropos is a Python framework from Nous Research for building reinforcement learning environments that collect and evaluate LLM trajectorie… | 10 | 1351 | abandoned |
| terry3041/pyChatGPT An unofficial Python wrapper that lets scripts interact with ChatGPT by automating a browser session, bypassing Cloudflare anti-bot protect… | 10 | 1335 | abandoned |
| acheong08/ChatGPTProxy A Go-based proxy server that bypasses Cloudflare protection on ChatGPT using TLS spoofing, exposing ChatGPT through an API-like interface. … | 10 | 1329 | abandoned |
| miurla/babyagi-ui BabyAGI UI is a Next.js web application that provides a ChatGPT-like interface for running and developing with the BabyAGI autonomous AI ag… | 10 | 1326 | abandoned |
| jayminwest/overstory Overstory is a TypeScript CLI that orchestrates multiple AI coding agents as a team, spawning workers in isolated git worktrees and coordin… | 10 | 1315 | abandoned |
| CommandCodeAI/BaseAI BaseAI is a TypeScript-first web AI framework for building serverless, composable AI agents with memory (RAG), tools, and pipes, developed … | 56 | 1283 | abandoned |
| jiran214/GPT-vup GPT-vup is a Python application that powers an AI-driven Live2D virtual streamer (VTuber) on BiliBili and Douyin live platforms. It uses Op… | 30 | 1277 | abandoned |
| Yanyutin753/PandoraNext-TokensTool A Java-based web management tool for PandoraNext that lets users manage tokens.json and config.json, auto-refresh share_token/access_token/… | 10 | 1277 | abandoned |
| ray-project/ray-llm RayLLM was a library for serving and deploying large language models on top of Ray, providing LLM APIs built on Ray Serve. It has been arch… | 10 | 1261 | abandoned |
| OpenRouterArchived/openrouter-runner A deprecated LLM inference engine built with vLLM by OpenRouter in its early days to serve niche fine-tuned models to early adopters. It is… | 10 | 1256 | abandoned |
| yuezk/chatgpt-mirror A self-hosted web application that mirrors the ChatGPT experience using the OpenAI gpt-3.5-turbo API. It runs on Node.js (or Docker) and se… | 10 | 1218 | abandoned |
| transitive-bullshit/bing-chat A Node.js/TypeScript client library wrapping Bing Chat's unofficial, reverse-engineered API, supporting conversations, streaming responses,… | 10 | 1203 | abandoned |
| langchain-ai/langchain-extract A FastAPI-based web server that uses LLMs to extract structured information from text and files, with extractors defined via JSON Schema an… | 10 | 1192 | abandoned |
| acheong08/ChatGPT-to-API A Go server that exposes an OpenAI-compatible chat completions API backed by ChatGPT's web interface, cycling through accounts and access t… | 10 | 1138 | abandoned |
| sugyan/claude-code-webui A web-based chat interface for the Claude Code CLI, providing streaming responses in a browser UI usable on desktop and mobile. Distributed… | 10 | 1137 | abandoned |
| pbloem/former A minimal, from-scratch implementation of the transformer architecture in PyTorch, accompanying a tutorial blog post on how modern transfor… | 34 | 1098 | abandoned |
| snowby666/poe-api-wrapper A Python API wrapper for Poe.com that provides unofficial access to various AI chatbots like GPT-4, Claude, Llama, Gemini, and Mistral thro… | 10 | 1093 | abandoned |
| google-gemini/deprecated-generative-ai-swift The deprecated Google AI Swift SDK for calling the Gemini API from Apple platform apps. It is explicitly obsolete and developers are direct… | 10 | 1073 | abandoned |
| pinecone-io/canopy Canopy is an open-source Retrieval Augmented Generation (RAG) framework and context engine built on top of the Pinecone vector database, pr… | 10 | 1033 | abandoned |
| dillionverma/llm.report llm.report is an open-source logging and analytics platform for the OpenAI API, letting users log ChatGPT API requests and responses, analy… | 10 | 1019 | abandoned |
| graykode/gpt-2-Pytorch A compact PyTorch reimplementation of OpenAI's GPT-2 for text generation, loading Hugging Face's converted pre-trained weights. It provides… | 32 | 1012 | abandoned |
| X Recommendation Algorithm The open-source source code for X's (formerly Twitter) recommendation algorithm, a set of services and jobs that serve personalized feeds o… | 45 | 73957 | active |
| OpenBB OpenBB's Open Data Platform (ODP) is an open-source Python toolset that integrates proprietary, licensed, and public financial data sources… | 85 | 73550 | active |
| Qlib Qlib is an AI-oriented quantitative investment platform from Microsoft that supports the full quant research workflow, from data processing… | 88 | 49589 | active |
| DeepSpeed DeepSpeed is an open‑source deep learning optimization library that enables efficient distributed training and inference of large models. I… | 98 | 43216 | active |
| Novu Novu is an open-source communication infrastructure platform that provides a unified API for sending notifications (in-app inbox, email, SM… | 92 | 40038 | active |
| block/buzz Buzz is a self-hostable team workspace where humans and AI agents collaborate in shared rooms, built on a Nostr relay where every message, … | 78 | 36110 | active |
| SurrealDB SurrealDB is a multi-model database written in Rust that combines document, graph, vector, and relational data models in a single ACID engi… | 93 | 33087 | stable |
| Envoy Envoy is a CNCF-hosted, high-performance C++ edge, middle, and service proxy designed for cloud-native and AI-native applications. It provi… | 95 | 29082 | stable |
| GitBook GitBook is an open‑source web application that renders documentation sites from Markdown and custom blocks. It provides a developer‑friendl… | 76 | 29064 | active |
| Apache SkyWalking Apache SkyWalking is an open-source APM (Application Performance Monitoring) platform for microservices, cloud-native, and container-based … | 88 | 24968 | stable |
| deepseek-ai/DeepSeek-OCR DeepSeek-OCR is an open vision-language model from DeepSeek AI that researches 'contexts optical compression' - encoding long text contexts… | 43 | 23965 | active |
| wandb/openui OpenUI is an open-source web application from Weights & Biases that generates UI components from natural language descriptions, rendering t… | 69 | 22573 | active |
| Eclipse Theia Eclipse Theia is an open-source framework written in TypeScript for building custom cloud (browser-based) and desktop IDEs and tools, with … | 98 | 21705 | active |