domain: large-language-models
3756 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| deepset-ai/haystack Haystack is an open-source Python AI orchestration framework by deepset for building production-ready LLM applications, agents, and RAG sys… | 99 | 26325 | stable |
| JustVugg/colibri Colibrì is a pure-C, zero-dependency inference engine that runs frontier Mixture-of-Experts models (744B to 2.8T parameters) on consumer ha… | 80 | 26251 | active |
| OpenBMB/MiniCPM-V MiniCPM-V and MiniCPM-o are a series of small multimodal large language models for efficient image, video, and audio understanding, deploya… | 61 | 26240 | active |
| xai-org/grok-build Grok Build is SpaceXAI's terminal-based AI coding agent, written in Rust, that runs as a full-screen interactive TUI. It understands codeba… | 57 | 26100 | active |
| Cinnamon/kotaemon Kotaemon is an open-source RAG-based application providing a clean, customizable UI for chatting and doing question answering with your own… | 84 | 25716 | active |
| mozilla-ai/llamafile llamafile is a Mozilla project that packages llama.cpp (and whisper.cpp for whisperfile) with Cosmopolitan Libc into single-file executable… | 94 | 25694 | active |
| Agent2Agent (A2A) Protocol Agent2Agent (A2A) is an open protocol, hosted under the Linux Foundation, that standardizes communication and interoperability between opaq… | 82 | 25503 | active |
| microsoft/OmniParser OmniParser is a screen parsing tool from Microsoft that converts UI screenshots into structured, understandable elements to ground vision-l… | 60 | 25310 | active |
| toon-format/toon TOON (Token-Oriented Object Notation) is a compact, human-readable encoding of the JSON data model designed to reduce token usage in LLM pr… | 83 | 25261 | active |
| microsoft/JARVIS JARVIS (HuggingGPT) is a system that uses an LLM as a controller to plan tasks and orchestrate numerous expert ML models from the HuggingFa… | 45 | 25208 | active |
| haotian-liu/LLaVA LLaVA (Large Language and Vision Assistant) is an open-source multimodal large language model framework implementing visual instruction tun… | 20 | 25000 | active |
| Dao-AILab/flash-attention Official implementation of FlashAttention, FlashAttention-2, -3, and -4: fast and memory-efficient exact attention kernels for GPUs. It acc… | 95 | 24787 | active |
| TencentCloud/TencentDB-Agent-Memory TencentDB Agent Memory is a self-hosted team-level memory hub for AI agents that converts conversations, docs, and code into four reusable … | 81 | 24677 | active |
| promptfoo/promptfoo Promptfoo is an open-source CLI and library for evaluating and red-teaming LLM applications, prompts, agents, and RAG pipelines. It support… | 92 | 24603 | active |
| google-ai-edge/gallery Google AI Edge Gallery is a mobile and desktop application for running open-source large language models like Gemma entirely on-device, off… | 86 | 24565 | active |
| deepseek-ai/DeepSeek-Coder DeepSeek Coder is a series of open code language models (1B to 33B) trained from scratch on 2T tokens of code and natural language, with a … | 50 | 24217 | active |
| Stagehand Stagehand is an SDK for building browser agents, offering Playwright-style APIs combined with AI primitives (act, extract, observe) that us… | 87 | 24069 | active |
| PaddlePaddle/Paddle PaddlePaddle is an industrial-grade deep learning framework written in C++ with Python APIs, supporting high-performance single-machine and… | 84 | 24062 | active |
| titanwings/distilly Distilly is a Python tool that distills a person's experience, judgment, voice, and working style from messages, documents, interviews, and… | 63 | 24016 | active |
| SuperClaude-Org/SuperClaude_Framework SuperClaude is a configuration framework that enhances Claude Code with 30 specialized slash commands, 20 cognitive personas, 7 behavioral … | 77 | 23842 | active |
| vanna-ai/vanna Vanna is an open-source Python framework for building user-aware AI agents that translate natural-language questions into SQL queries, char… | 10 | 23818 | active |
| sinaptik-ai/pandas-ai PandasAI is a Python library that lets users query data in SQL, CSV, or parquet format using natural language, powered by LLMs and RAG. It … | 57 | 23772 | active |
| coleam00/Archon Archon is an open-source workflow engine for AI coding agents that lets you define development processes (planning, implementation, validat… | 87 | 23276 | active |
| verl-project/verl verl (Volcano Engine Reinforcement Learning) is a flexible, production-ready RL post-training library for large language models, open-sourc… | 84 | 23145 | active |
| mlc-ai/mlc-llm MLC LLM is a machine learning compiler and high-performance deployment engine for large language models, built on TVM-based ML compilation.… | 64 | 23095 | active |
| different-ai/openwork OpenWork is a free, open-source desktop app for building and sharing AI agent workflows, positioned as an open-source alternative to Claude… | 78 | 23093 | active |
| HKUDS/RAG-Anything RAG-Anything is an all-in-one Python framework for multimodal Retrieval-Augmented Generation, built on LightRAG. It treats text, images, ta… | 80 | 23081 | active |
| micro/go-micro Go Micro is a Go framework and CLI that combines an AI agent harness with a microservices framework, giving agents tools, memory, guardrail… | 95 | 23043 | active |
| QwenAudio/CosyVoice CosyVoice is a multilingual large voice generation model (TTS) with full-stack inference, training, and deployment support. It offers zero-… | 61 | 22925 | active |
| 1Panel-dev/MaxKB MaxKB is an open-source, self-hosted platform for building enterprise-grade AI agents with RAG pipelines, workflow orchestration, and MCP t… | 94 | 22612 | active |
| BuilderIO/gpt-crawler A Node.js/TypeScript crawler that scrapes one or more websites and generates knowledge files (JSON) for creating custom GPTs or OpenAI assi… | 31 | 22393 | active |
| winfunc/opcode opcode is a Tauri-based desktop GUI application and toolkit for managing Claude Code, Anthropic's CLI coding agent. It provides visual proj… | 43 | 22383 | active |
| NVIDIA/NemoClaw NVIDIA NemoClaw is an open-source reference stack for running AI coding agents such as OpenClaw, Hermes, and LangChain Deep Agents Code sec… | 59 | 22287 | active |
| claude-code-best/claude-code An open-source, buildable and debuggable reimplementation of Anthropic's Claude Code terminal-native agentic coding system, written in Type… | 79 | 22224 | active |
| PromtEngineer/localGPT LocalGPT is a fully private, on-premise document intelligence platform that lets users chat with, summarize, and query their own documents … | 74 | 22205 | active |
| microsoft/unilm Microsoft's collection of large-scale self-supervised pre-trained models spanning tasks, 100+ languages, and modalities (text, image, layou… | 67 | 22194 | active |
| wavetermdev/waveterm Wave Terminal is an open-source, cross-platform terminal emulator with integrated AI assistance, durable SSH sessions, file previews, a bui… | 92 | 22112 | active |
| vxcontrol/pentagi PentAGI is a self-hosted, fully autonomous multi-agent AI system for performing complex penetration testing tasks, built in Go with a React… | 78 | 22033 | active |
| jina-ai/serve Jina-serve is a Python framework for building and deploying multimodal AI services that communicate via gRPC, HTTP, and WebSockets. It prov… | 40 | 21861 | active |
| antirez/ds4 DwarfStar (ds4) is a self-contained native LLM inference engine written in C, optimized for DeepSeek V4 Flash and PRO and GLM 5.2, with sup… | 58 | 21807 | active |
| guidance-ai/guidance Guidance is a Python library providing an efficient programming paradigm for steering large language models, letting you interleave control… | 79 | 21714 | active |
| microsoft/onnxruntime ONNX Runtime is a cross-platform, high-performance machine-learning accelerator for running inference and training on ONNX models. It suppo… | 99 | 21654 | stable |
| snarktank/ralph Ralph is an autonomous AI agent loop that repeatedly runs AI coding tools like Amp or Claude Code until all items in a product requirements… | 45 | 21627 | active |
| comet-ml/opik Opik is an open-source LLM observability and evaluation platform by Comet for tracing, evaluating, and monitoring LLM applications, RAG pip… | 92 | 21624 | active |
| huggingface/peft PEFT is a Python library from Hugging Face providing state-of-the-art parameter-efficient fine-tuning methods (LoRA, adapters, soft prompts… | 93 | 21598 | stable |
| HKUDS/AI-Trader AI-Trader is an agent-native trading platform where autonomous AI agents register, trade, and compete with live mark-to-market scoring and … | 56 | 21561 | active |
| coze-dev/coze-studio Coze Studio is an open-source, all-in-one AI agent development platform with visual, no-code/low-code tools for building, debugging, and de… | 73 | 21506 | active |
| openobserve/openobserve OpenObserve is an open-source, cloud-native observability platform that unifies logs, metrics, traces, RUM, and LLM observability in a sing… | 93 | 21490 | active |
| dyad-sh/dyad Dyad is a free, local, open-source desktop AI app builder that turns natural-language prompts into working full-stack web apps, positioned … | 82 | 21322 | active |
| Agent Development Kit (ADK) Agent Development Kit (ADK) is Google's open-source, code-first framework for building, evaluating, and deploying AI agents, available in P… | 82 | 21299 | active |
| vectorize-io/hindsight Hindsight is an open-source agent memory system that gives AI agents persistent long-term memory that learns and consolidates knowledge ove… | 79 | 21228 | active |
| AI4Finance-Foundation/FinGPT FinGPT is an open-source financial large language model project from the AI4Finance Foundation, providing domain-tuned models, fine-tuning … | 77 | 21154 | active |
| huggingface/candle Candle is a minimalist machine learning framework for Rust focused on performance and ease of use, with CPU and CUDA GPU support. It ships … | 73 | 20955 | active |
| THU-MAIC/OpenMAIC OpenMAIC is an open-source multi-agent interactive classroom that delivers immersive AI-driven learning experiences with one click. Built w… | 81 | 20934 | active |
| vercel/chatbot A full-featured, hackable Next.js AI chatbot template built by Vercel on top of the AI SDK, with chat history persistence, authentication, … | 70 | 20876 | active |
| jundot/omlx oMLX is a native macOS menu bar application and LLM inference server built on Apple's MLX framework, featuring continuous batching and two-… | 78 | 20760 | active |
| anywhere-labs/dsh-desktop DSH Desktop is a community-maintained open-source desktop client for Windows and macOS that wraps the DeepSeek Harness local Web UI, host s… | 79 | 20723 | active |
| cube-js/cube Cube Core is an open-source semantic layer that lets teams define metrics, dimensions, joins, and access rules in code, then serve them thr… | 95 | 20711 | active |
| Tencent/WeKnora WeKnora is an open-source, LLM-powered knowledge platform by Tencent that turns raw documents into a queryable RAG system, an autonomous Re… | 84 | 20700 | active |
| tashfeenahmed/freellmapi FreeLLMAPI is an open-source, self-hosted LLM gateway that aggregates free tiers from 34 providers (600+ free model endpoints) behind a sin… | 81 | 20682 | active |
| pingdotgg/t3code T3 Code is an open-source 'agent harness control surface' that lets you orchestrate coding agents like Claude Code, Codex, Cursor, Grok Bui… | 82 | 20622 | active |
| openai/gpt-oss OpenAI's gpt-oss repository hosts reference implementations and tooling for two open-weight language models, gpt-oss-120b and gpt-oss-20b, … | 71 | 20347 | stable |
| mksglu/context-mode An open-source MCP plugin that optimizes AI coding agent context windows by intercepting large tool outputs, storing them in a local FTS5 i… | 74 | 20167 | active |
| kortix-ai/suna Kortix is an open-source AI Management System where AI agents, skills, memory, and connectors are defined as files in a git repo. Agents ru… | 85 | 20141 | active |
| camel-ai/owl OWL is a multi-agent collaboration framework built on the CAMEL-AI framework for automating real-world tasks through dynamic agent interact… | 64 | 20104 | active |
| KKKKhazix/khazix-skills A collection of open-source AI Agent Skills following the Agent Skills open standard, installable into Claude Code, Codex, Cursor, and 40+ … | 58 | 20097 | active |
| karpathy/llama2.c A minimal, dependency-free implementation of the Llama 2 LLM architecture that trains in PyTorch and runs inference in a single ~700-line p… | 28 | 20028 | active |
| Alibaba-NLP/DeepResearch Tongyi DeepResearch is an open-source agentic large language model (30.5B total parameters, 3.3B activated per token) plus training and inf… | 52 | 19878 | active |
| Nagi-ovo/voyager Voyager is a browser extension enhancement suite for AI chat web UIs like Gemini, AI Studio, Claude, and ChatGPT, adding features such as c… | 80 | 19848 | active |
| QwenLM/Qwen3-VL Qwen3-VL is a series of open-weight multimodal vision-language models from Alibaba's Qwen team, available in Dense and MoE architectures wi… | 52 | 19847 | active |
| dzhng/deep-research An AI-powered deep research agent that iteratively generates search queries, scrapes web content, and refines its research direction using … | 55 | 19603 | active |
| refactoringhq/tolaria Tolaria is an open-source desktop app for macOS, Windows, and Linux for managing markdown knowledge bases, built with Tauri and TypeScript.… | 77 | 19593 | active |
| pydantic/pydantic-ai Pydantic AI is a type-safe Python SDK for building AI agents and LLM applications, with a typed agent loop, structured outputs, tool callin… | 86 | 19518 | active |
| kvcache-ai/ktransformers KTransformers is a Python/C++ framework for CPU-GPU heterogeneous inference and fine-tuning of large language models, with a kt-kernel back… | 90 | 19303 | active |
| openai/evals OpenAI Evals is a Python framework for evaluating large language models and LLM-based systems, with an open-source registry of benchmark ev… | 66 | 19262 | active |
| elizaOS/eliza elizaOS is an open-source TypeScript framework and product stack for building and running autonomous AI agents, including a core runtime, C… | 90 | 19176 | active |
| huggingface/trl TRL is a Hugging Face library for post-training transformer language models with techniques like Supervised Fine-Tuning (SFT), GRPO, DPO, K… | 99 | 19155 | active |
| openai/tiktoken tiktoken is a fast byte pair encoding (BPE) tokenizer library for Python built for OpenAI's language models, converting text into reversibl… | 89 | 19102 | stable |
| agent0ai/agent-zero Agent Zero is an open-source agentic AI framework that gives LLM-powered agents a full Dockerized Linux computer, including a desktop, brow… | 86 | 18978 | active |
| lss233/kirara-ai Kirara AI is a self-hosted, DIY multimodal AI chatbot framework that connects large language models (DeepSeek, ChatGPT, Claude, Gemini, Oll… | 46 | 18972 | active |
| teng-lin/notebooklm-py An unofficial Python SDK, CLI, and agentic skill for programmatically driving Google NotebookLM (now Gemini Notebook), including source imp… | 82 | 18951 | active |
| state-spaces/mamba Mamba is a PyTorch library implementing the selective state space model (SSM) architecture for linear-time sequence modeling, with hardware… | 85 | 18783 | active |
| danielmiessler/LifeOS LifeOS is an open-source, AI-powered 'life operating system' that captures your goals, context, and ideal state, then uses that personal co… | 83 | 18751 | active |
| PrimeIntellect-ai/prime-agent Prime Agent is an open-source coding and research agent built around Recursive Language Models (RLM) and a Continual Harness that stores pr… | 81 | 18642 | active |
| 1jehuang/jcode jcode is an open-source AI coding agent for the terminal, written in Rust, that lets developers run many agent sessions in parallel with ve… | 78 | 18635 | active |
| WebLLM WebLLM is a high-performance in-browser LLM inference engine that runs language models entirely client-side using WebGPU hardware accelerat… | 85 | 18603 | active |
| emcie-co/parlant Parlant is an open-source Python framework that acts as an interaction control harness for building reliable, customer-facing LLM agents. I… | 83 | 18269 | active |
| arc53/DocsGPT DocsGPT is an open-source AI platform for building private agents, assistants, and enterprise search over your own documents. It includes a… | 93 | 18229 | active |
| ccusage/ccusage ccusage is a fast local CLI that analyzes token usage and estimated costs from coding agent CLIs such as Claude Code, Codex, OpenCode, Gemi… | 81 | 18176 | active |
| xming521/WeClone WeClone is an end-to-end Python framework for creating a personal AI digital twin by fine-tuning large language models on your exported cha… | 80 | 18171 | active |
| langchain-ai/langchainjs LangChain.js is a TypeScript framework for building LLM-powered applications, providing standard interfaces for agents, models, embeddings,… | 93 | 18135 | active |
| RightNow-AI/openfang OpenFang is an open-source Agent Operating System written in Rust that runs autonomous AI agents on schedules, 24/7, with pre-built capabil… | 68 | 18135 | active |
| confident-ai/deepeval DeepEval is an open-source Python framework for evaluating LLM applications with pytest-style unit tests and 50+ research-backed metrics in… | 95 | 17882 | active |
| microsoft/agent-lightning Agent Lightning is a lightweight (~3,500-line) agentic reinforcement learning framework from Microsoft for training LLM-powered agents with… | 85 | 17863 | active |
| AsyncFuncAI/deepwiki-open DeepWiki-Open (now Grok-Wiki) is an open-source, AI-powered tool that automatically generates interactive wikis, documentation, diagrams, a… | 63 | 17787 | active |
| nesquena/hermes-webui Hermes WebUI is a lightweight, dark-themed web interface for the Hermes Agent, providing full CLI parity from a browser or phone. It runs a… | 77 | 17759 | active |
| deepseek-ai/Janus Janus-Series is DeepSeek's family of unified multimodal models (Janus, Janus-Pro, JanusFlow) that combine multimodal understanding and imag… | 24 | 17757 | active |
| camel-ai/camel CAMEL is an open-source Python framework for building multi-agent AI systems, providing agents, role-based societies, memory, RAG pipelines… | 84 | 17646 | active |
| NVIDIA/Megatron-LM NVIDIA's GPU-optimized library for training large transformer models at scale, comprising Megatron-LM (reference training scripts) and Mega… | 99 | 17615 | active |
| langbot-app/LangBot LangBot is an open-source, production-grade platform for building AI-powered instant messaging bots, connecting LLMs and agent workflows to… | 94 | 17558 | active |