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 |
|---|---|---|---|
| Eynzof/Hermes-CN-Desktop A Windows-first desktop client for Hermes Agent built by the Chinese-language Hermes Agent community, using Tauri v2, Rust, React, and Type… | 79 | 1712 | experimental |
| skyllwt/AutoSci AutoSci is a wiki-centric AI research platform that automates the full scientific research lifecycle — reading literature, thinking, runnin… | 58 | 1689 | experimental |
| lorryjovens-hub/claude-code-rust A Tauri 2.0 desktop application (Rust backend, React 19 frontend) that wraps multiple LLM providers like Anthropic, OpenAI, and DeepSeek in… | 49 | 1662 | experimental |
| eylonmiz/react-agent ReactAgent is an open-source autonomous LLM agent that uses GPT-4 to generate and compose React components from user stories. It is built w… | 21 | 1656 | experimental |
| abundantbeing/hermes-browser-extension A Chrome/Edge/Chromium side-panel browser extension that connects active web context to a Hermes Agent runtime via a local gateway, Hermes … | 80 | 1655 | experimental |
| deepseek-ai/DeepSeek-V3.2-Exp DeepSeek-V3.2-Exp is an experimental open-weight large language model release that introduces DeepSeek Sparse Attention for more efficient … | 37 | 1654 | experimental |
| SETA OWL is a Python‑based framework that enables multiple AI agents to collaborate on real‑world task automation. It builds on the CAMEL‑AI eco… | 60 | 179 | active |
| collabora/WhisperFusion WhisperFusion is a real-time voice chat application that combines WhisperLive speech-to-text, a Mistral/Phi LLM, and WhisperSpeech text-to-… | 27 | 1648 | experimental |
| EvolvingLMMs-Lab/open-r1-multimodal A fork of Hugging Face's open-r1 that extends the R1 GRPO reinforcement learning training paradigm to multimodal (vision-language) models l… | 21 | 1606 | experimental |
| lyuchenyang/Macaw-LLM Macaw-LLM is a multi-modal language modeling framework that integrates image, video, audio, and text data, built on CLIP, Whisper, and LLaM… | 30 | 1591 | experimental |
| cyberpapiii/chipotlai-max Chipotlai Max is a meme fork of the OpenCode AI coding agent that hardcodes Chipotle's reverse-engineered 'Pepper' support chatbot as the d… | 50 | 1572 | experimental |
| ghuntley/loom Loom is an AI-powered coding agent written in Rust that provides a REPL interface for interacting with LLM-driven agents capable of file sy… | 61 | 1567 | experimental |
| AnswerDotAI/fsdp_qlora A training script/library from Answer.AI that combines QLoRA (quantized LoRA) with PyTorch FSDP to fine-tune large language models like Lla… | 27 | 1554 | experimental |
| xxnuo/open-coreui Open CoreUI is a lightweight Rust rewrite of Open WebUI that provides a chat interface for LLMs without Docker, Python, or database depende… | 55 | 1538 | experimental |
| protectai/rebuff Rebuff is a self-hardening prompt injection detector that protects LLM-powered applications through multi-layered defenses: heuristics, a d… | 10 | 1521 | experimental |
| YGYOOO/WorldX WorldX is an open-source web application that generates an AI-driven virtual world from a single sentence, creating maps, pixel-art charact… | 58 | 1512 | experimental |
| chmod777john/swarm-ide Swarm-IDE is a self-hosted IDE for orchestrating self-organizing agent swarms, where agents dynamically create sub-agents and communicate v… | 44 | 1501 | experimental |
| daveshap/ACE_Framework ACE (Autonomous Cognitive Entities) is an open-source framework for building fully autonomous AI agents that run entirely on local hardware… | 10 | 1501 | experimental |
| murtaza-nasir/maestro MAESTRO is a self-hosted AI-powered research platform that plans and executes complex research tasks using AI agents. It generates detailed… | 54 | 1492 | experimental |
| Learning to (Learn at Test Time) Language Model Official PyTorch implementation of Test-Time Training (TTT) layers, a sequence modeling layer with linear complexity whose hidden state is … | 24 | 1405 | experimental |
| jdagdelen/hyperDB HyperDB is a lightweight, local vector database library for Python with a C++/MKL-accelerated backend, designed to store and query document… | 21 | 1401 | experimental |
| Parallax Parallax is a distributed model serving framework that lets you build your own AI cluster across heterogeneous, geographically dispersed de… | 61 | 1397 | experimental |
| justrach/codedb codedb is a Zig-based code intelligence server that indexes a codebase once and serves structural queries (symbols, outlines, trigram searc… | 76 | 1395 | experimental |
| socketteer/loom Loom is an experimental tree-based writing interface for collaborating with GPT-3, letting users explore branching continuations of a text … | 32 | 1390 | experimental |
| AutoArk/TinyEngram TinyEngram is an open research project exploring DeepSeek-AI's Engram architecture and memory injection as an alternative to LoRA for param… | 50 | 1380 | experimental |
| gorilla-llm/gorilla-cli Gorilla CLI is a command-line tool that turns plain-English objectives into candidate shell commands using LLMs like Gorilla LLM, GPT-4, an… | 20 | 1374 | experimental |
| OpenBB-finance/experimental-openbb-platform-agent A Python library and R&D playground from OpenBB that builds LLM-powered financial analyst agents on top of the OpenBB Platform. Agents use … | 18 | 1348 | experimental |
| linyiLYi/voice-assistant A simple single-script Python demo of a local voice assistant that uses Whisper (via Apple MLX) for speech recognition and a local Yi large… | 27 | 1323 | experimental |
| Claw-AI-Lab/Claw-AI-Lab Claw AI Lab is a self-hosted multi-agent platform that simulates a full AI research lab from a single prompt, orchestrating specialized age… | 51 | 1315 | experimental |
| DLYuanGod/TinyGPT-V TinyGPT-V is an efficient multimodal large language model built on small backbones (Phi-2 2.7B), combining vision and language capabilities… | 53 | 1314 | experimental |
| anc95/writely Writely is an open-source browser extension for Chrome, Firefox, and Edge that brings GPT-powered AI writing assistance to any editable web… | 33 | 1296 | experimental |
| microsoft/prompty Prompty is a markdown-based file format (.prompty) for authoring LLM prompts with YAML frontmatter for model config, inputs, tools, and tem… | 91 | 1285 | experimental |
| Runfusion/Fusion Fusion is an open-source multi-agent orchestrator that acts as a 'software factory': AI agents plan, build, review, and ship code from plai… | 80 | 1280 | experimental |
| mozilla-ai/cq cq is an open standard and tooling for shared agent learning: AI coding agents persist, share, and query structured knowledge units so they… | 73 | 1275 | experimental |
| KhoomeiK/LlamaGym LlamaGym is a Python library that simplifies fine-tuning LLM-based agents with online reinforcement learning in Gym-style environments. It … | 26 | 1253 | experimental |
| openairymax/agentrt AgentRT is an OS-grade runtime platform for AI agent teams, providing primitives for orchestrating, scheduling, isolating, and observing ag… | 83 | 1252 | experimental |
| nethical6/conversation-steganography A Go CLI tool that hides encrypted secret messages inside natural-looking chat text generated by a local LLM (GPT-2), enabling covert commu… | 52 | 1250 | experimental |
| microsoft/powerbi-modeling-mcp A local MCP server from Microsoft that exposes Power BI semantic modeling capabilities to AI agents, enabling natural-language creation and… | 71 | 1240 | experimental |
| SakanaAI/self-adaptive-llms Transformer² is a research framework from SakanaAI that adapts large language models to unseen tasks in real-time by selectively adjusting … | 22 | 1225 | experimental |
| NoDataFound/hackGPT hackGPT is a Python/Jupyter-based chatbot application that leverages OpenAI and ChatGPT APIs for security-oriented tasks like malware analy… | 72 | 1212 | experimental |
| Jamie-Stirling/RetNet A minimal, pure PyTorch implementation of the Retentive Network (RetNet) architecture proposed as a successor to Transformers for large lan… | 29 | 1212 | experimental |
| cinderline/northcinder NorthCinder is a self-hosted MCP server that acts as a buyer-side shopping agent, comparing products across user-chosen sources and explain… | 73 | 1208 | experimental |
| soongenwong/claudecode An open-source, Rust-based terminal AI coding agent inspired by Anthropic's Claude Code, offering an interactive agent shell, one-shot prom… | 51 | 1207 | experimental |
| danielgross/LlamaAcademy LlamaAcademy is a Python pipeline that crawls API documentation, generates synthetic training data with GPT-3.5/GPT-4, and fine-tunes a Vic… | 30 | 1197 | experimental |
| tspeterkim/flash-attention-minimal A minimal ~100-line CUDA re-implementation of the Flash Attention forward pass, loadable as a PyTorch extension. It is designed as an educa… | 26 | 1192 | experimental |
| Ido-Levi/Hephaestus Hephaestus is a Python-based semi-structured agentic framework where AI agents dynamically create tasks and build workflows as they discove… | 33 | 1185 | experimental |
| google-deepmind/synthid-text A reference Python implementation of Google DeepMind's SynthID Text watermarking and detection technology for identifying AI-generated text… | 68 | 1173 | experimental |
| farzaa/gemini-bball A demo project from a viral tweet that uses Google's Gemini API to analyze basketball video frames, with an OpenCV-based visualizer. The co… | 29 | 1163 | experimental |
| Axflow Axflow is a modular TypeScript framework for building natural language powered AI applications, composed of packages like @axflow/models (S… | 20 | 1122 | experimental |
| agents-io/PokeClaw PokeClaw is an open-source Android app that runs an on-device LLM (Gemma 4 via LiteRT) to control and automate your phone, with no cloud or… | 65 | 1083 | experimental |
| thinking-machines-lab/batch_invariant_ops A Python library that replaces standard PyTorch CUDA kernels with batch-invariant versions, ensuring identical results regardless of batch … | 37 | 1080 | experimental |
| Nile Nile is a Postgres platform re-engineered for multi-tenant B2B applications, decoupling storage from compute and virtualizing tenants withi… | 72 | 1077 | experimental |
| srush/llama2.rs A pure Rust implementation of Llama2 inference optimized for fast CPU execution, featuring 4-bit GPT-Q quantization, SIMD support, and memo… | 29 | 1064 | experimental |
| yoheinakajima/ditto Ditto is a simple self-building coding agent that generates multi-file Flask applications from natural language descriptions via a web inte… | 23 | 1064 | experimental |
| Omniplex-ai/omniplex Omniplex is an open-source, self-hosted alternative to Perplexity, an AI-powered answer engine that combines web search with LLMs to genera… | 25 | 1060 | experimental |
| philippgille/chromem-go chromem-go is an embeddable vector database for Go with a Chroma-like interface and zero third-party dependencies. It runs in-memory with o… | 59 | 1059 | experimental |
| volcengine/veScale veScale is a PyTorch distributed training library from ByteDance for hyperscale training of large language models and reinforcement learnin… | 54 | 1041 | experimental |
| huggingface/optimum-nvidia Optimum-NVIDIA is a Python library that bridges Hugging Face Transformers with NVIDIA TensorRT-LLM for highly optimized LLM inference on NV… | 62 | 1039 | experimental |
| trotsky1997/MathBlackBox MathBlackBox (MCTSr) is a Python research implementation of Monte Carlo Tree Self-Refine, an algorithm that combines MCTS with LLM self-ref… | 24 | 1032 | experimental |
| HumanMLLM/R1-Omni R1-Omni is a research project applying Reinforcement Learning with Verifiable Reward (RLVR) to an omni-multimodal large language model for … | 22 | 1025 | experimental |
| DeepWism/DeepWism-R2 DeepWism R2 is an AI 'Research&Report' system presented as a next-generation AGI agents framework built on a Thin-Thick-Thin Crowd Entropy … | 28 | 1017 | experimental |
| openai/openai-realtime-api-beta A Node.js and browser reference client library for OpenAI's Realtime API, enabling real-time voice and text conversations with GPT models. … | 23 | 1016 | experimental |
| victordibia/autogen-ui A web UI for Microsoft's AutoGen AgentChat API, providing a chat interface to interact with a predefined multi-agent team. It pairs a FastA… | 28 | 1007 | experimental |
| susiai/susi_shell A suite of Python-based command line tools for interacting with AI services directly from the terminal, including chat, text completion, tr… | 37 | 1000 | experimental |
| meta-llama/llama Meta's official repository containing inference code and download scripts for Llama 2 large language models (7B to 70B parameters). The rep… | 31 | 59632 | abandoned |
| Flowise Flowise is an open‑source visual development platform for building AI agents and LLM workflows. It provides a web UI, CLI, and APIs to desi… | 10 | 55501 | abandoned |
| Flowise Flowise is an open-source, visual low-code platform for building AI agents, chatbots, and LLM workflows using a drag-and-drop builder with … | 10 | 55501 | abandoned |
| LAION-AI/Open-Assistant OpenAssistant is an open-source chat-based assistant that understands tasks, interacts with third-party systems, and retrieves information … | 23 | 37370 | abandoned |
| Pythagora-io/gpt-pilot GPT Pilot was an AI coding agent that aimed to act as an 'AI developer', generating full applications step-by-step from a specification usi… | 65 | 33662 | abandoned |
| voideditor/void Void is an open-source AI code editor forked from VS Code, offering chat, agent mode, inline edits, and autocomplete with any LLM provider … | 10 | 28781 | abandoned |
| openai/gpt-2 Official OpenAI repository containing code and pretrained model weights for GPT-2, from the paper 'Language Models are Unsupervised Multita… | 10 | 25009 | abandoned |
| Roo Code Roo Code is a VS Code extension that provides a team of AI coding agents inside the editor, with modes for coding, architecture planning, d… | 10 | 24296 | abandoned |
| openai/swarm Swarm is an experimental, educational Python framework from OpenAI for lightweight multi-agent orchestration, built on the Chat Completions… | 57 | 22004 | abandoned |
| QwenLM/Qwen The official repository for Qwen (Tongyi Qianwen), Alibaba Cloud's family of pretrained and chat large language models, with weights on Hug… | 57 | 21858 | abandoned |
| transitive-bullshit/agentic Agentic is a marketplace and hosted MCP gateway that turns any MCP server or OpenAPI service into a paid, production-ready MCP product with… | 10 | 18103 | abandoned |
| richards199999/Thinking-Claude Thinking Claude is a browser extension plus a set of 'thinking protocol' system instructions that make Claude's chat interface show an expl… | 55 | 17028 | abandoned |
| opencode-ai/opencode OpenCode is a terminal-based AI coding agent written in Go, providing a TUI for interacting with multiple AI providers (OpenAI, Anthropic, … | 10 | 13767 | abandoned |
| Jiayi-Pan/TinyZero TinyZero is a minimal reproduction of DeepSeek R1-Zero, showing that a 3B base language model can develop self-verification and search abil… | 49 | 13248 | abandoned |
| fuergaosi233/wechat-chatgpt A TypeScript bot that connects OpenAI's ChatGPT API to WeChat using the wechaty library, supporting text conversations, DALL·E image genera… | 23 | 13229 | abandoned |
| idootop/mi-gpt MiGPT is a Node.js/Docker application that connects Xiaomi's XiaoAI smart speakers to ChatGPT and Doubao, turning them into custom AI voice… | 10 | 12499 | abandoned |
| humanlayer/humanlayer HumanLayer is a multiplayer coding agent IDE and cloud control plane for orchestrating AI coding agents, bringing agent sessions, plan arti… | 71 | 11703 | abandoned |
| mistralai/mistral-inference The official minimal Python library from Mistral AI for running inference with Mistral open-weight models such as Mistral 7B, Mixtral, Code… | 10 | 10824 | abandoned |
| GitHub Copilot Chat The GitHub Copilot Chat extension for Visual Studio Code, providing AI chat, inline suggestions, and autonomous agent capabilities inside t… | 10 | 9960 | abandoned |
| intel/ipex-llm IPEX-LLM is a PyTorch LLM acceleration library for Intel hardware (iGPU, NPU, Arc/Flex/Max GPUs, and CPU), offering low-bit quantization (F… | 10 | 8845 | abandoned |
| OptiMate OptiMate is a collection of Python libraries from Nebuly AI for optimizing AI model performance, including Speedster for inference accelera… | 23 | 8328 | abandoned |
| EleutherAI/gpt-neo GPT-Neo is EleutherAI's implementation of model- and data-parallel GPT-3-style transformer language models built on mesh-tensorflow, with r… | 10 | 8255 | abandoned |
| acheong08/EdgeGPT A Python library that reverse engineers Microsoft's Bing Chat (EdgeGPT) API, providing unofficial programmatic access to Bing AI conversati… | 10 | 7836 | abandoned |
| gsd-build/gsd-2 GSD 2 is a meta-prompting, context engineering, and spec-driven development system that lets AI coding agents work autonomously for long pe… | 10 | 7771 | abandoned |
| weaviate/Verba Verba is an open-source end-to-end RAG application built on Weaviate, providing a user-friendly interface for ingesting data and chatting w… | 10 | 7704 | abandoned |
| ChatAnyTeam/ChatAny ChatAny is a self-hostable web application that aggregates ChatGPT-style AI chat with AI image generation services like Midjourney and Stab… | 51 | 6492 | abandoned |
| rustformers/llm An ecosystem of Rust libraries built on GGML for running large language model inference locally, including a CLI binary and reusable crates… | 10 | 6155 | abandoned |
| Lightning-AI/lit-llama Lit-LLaMA is an independent, Apache 2.0-licensed implementation of the LLaMA language model built on nanoGPT, covering pre-training, fine-t… | 40 | 6080 | abandoned |
| timescale/pgai pgai is a Python library and set of PostgreSQL tools from Timescale that turns PostgreSQL into a retrieval engine for RAG and agentic appli… | 10 | 5802 | abandoned |
| ramon-victor/freegpt-webui A Python web application providing a ChatGPT-style chat UI backed by the G4F (gpt4free) API, allowing access to GPT-3.5/4 models without an… | 10 | 5611 | abandoned |
| 21st-dev/1code 1Code is an open-source desktop and web client for orchestrating coding agents like Claude Code and Codex, with a Cursor-like UI, diff prev… | 10 | 5582 | abandoned |
| dsdanielpark/Bard-API An unofficial Python package that returns Google Bard (now Gemini) responses by reverse-engineering the web interface using cookie values i… | 10 | 5164 | abandoned |
| opencx-labs/copilot A TypeScript library for building AI copilot/sidekick experiences powered by large language models. The project is no longer maintained, pe… | 10 | 5109 | abandoned |
| iFlow CLI iFlow CLI is a terminal-based AI coding assistant that analyzes repositories, executes coding tasks, and automates workflows using free AI … | 47 | 5084 | abandoned |
| Cube Studio Cube Studio is an open-source, cloud-native, one-stop machine learning platform covering the full MLOps lifecycle: online notebooks, drag-a… | 79 | 5079 | abandoned |
| AutoGPTQ/AutoGPTQ AutoGPTQ is a Python library for quantizing large language models using the GPTQ weight-only quantization algorithm, with user-friendly API… | 10 | 5065 | abandoned |