function: llm-inference
3362 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| browseros-ai/BrowserOS BrowserOS is an open-source, Chromium-based agentic browser that lets AI agents (Claude Code, Codex, Cursor, MCP agents) drive a real brows… | 81 | 13360 | active |
| doocs/md A clean, web-based Markdown editor that instantly renders Markdown into WeChat Official Account-compatible rich text, with custom themes, d… | 83 | 13244 | active |
| livekit/agents LiveKit Agents is an open-source framework for building realtime, multimodal voice AI agents that run as programmable participants in LiveK… | 90 | 13176 | active |
| QwenLM/Qwen3-TTS Qwen3-TTS is a series of open-source text-to-speech models from Alibaba's Qwen team, supporting expressive and streaming speech generation,… | 48 | 13113 | active |
| Vaibhavs10/insanely-fast-whisper A CLI tool for transcribing audio files on-device using OpenAI's Whisper models, powered by Hugging Face Transformers, Optimum, and Flash A… | 49 | 13049 | active |
| zai-org/CogVideo CogVideo/CogVideoX is an open-source family of text-to-video and image-to-video generation models from Zhipu AI (THUDM), with inference and… | 45 | 12977 | active |
| neuml/txtai txtai is an all-in-one open-source AI framework for semantic search, LLM orchestration and language model workflows, built around an embedd… | 98 | 12909 | active |
| StarTrail-org/LEANN LEANN is a low-storage vector index that enables retrieval-augmented generation (RAG) on personal devices by recomputing embeddings on the … | 77 | 12836 | active |
| InsForge/InsForge InsForge is an open-source, all-in-one backend platform (BaaS) designed for AI coding agents, bundling Postgres, auth, storage, realtime, e… | 84 | 12784 | active |
| langchain-ai/open_deep_research An open-source deep research agent built with LangGraph that performs multi-step web research using configurable LLM providers, search tool… | 10 | 12673 | active |
| nearai/ironclaw IronClaw is an open-source, Rust-based 'Agent OS' and personal AI assistant that runs locally or on NEAR AI Cloud, with a WebUI, terminal, … | 82 | 12607 | active |
| Wei-Shaw/claude-relay-service A self-hosted relay/proxy service for Claude Code (and OpenAI, Gemini, Droid) subscriptions that lets multiple users share accounts via ind… | 83 | 12566 | active |
| Tencent-Hunyuan/HunyuanVideo HunyuanVideo is Tencent's open-source framework for large-scale video generation, providing PyTorch model definitions, pre-trained weights,… | 62 | 12476 | active |
| ubicloud/ubicloud Ubicloud is an open-source IaaS cloud platform that provides elastic compute (VMs), block storage, networking, load balancing, managed Post… | 76 | 12254 | active |
| HKUDS/ViMax ViMax is an agentic video generation framework that uses coordinated multi-agent collaboration (director, screenwriter, producer, video gen… | 72 | 12108 | active |
| FlagOpen/FlagEmbedding FlagEmbedding is the official Python toolkit for BAAI's BGE family of embedding models and rerankers, covering inference, evaluation, and f… | 87 | 12086 | active |
| h2oai/h2ogpt h2oGPT is an Apache-2.0 open-source application for chatting with local, private LLMs and querying/summarizing your own documents (PDFs, Wo… | 10 | 11969 | active |
| Tongyi-MAI/Z-Image Z-Image is a 6B-parameter text-to-image generation foundation model family built on a single-stream diffusion transformer, with a distilled… | 46 | 11944 | active |
| jina-ai/reader Jina AI Reader converts any URL into LLM-friendly markdown via the r.jina.ai prefix, and searches the web into markdown via s.jina.ai. It r… | 62 | 11912 | active |
| dataelement/bisheng BISHENG is an open-source LLM DevOps (LLMOps) platform for building enterprise AI applications, offering GenAI workflow orchestration, RAG,… | 94 | 11911 | active |
| zaidmukaddam/scira Scira is an open-source, minimalistic AI-powered search engine and agentic research platform that plans multi-step searches, retrieves live… | 67 | 11850 | active |
| facebookresearch/seamless_communication A library of foundational multilingual multimodal AI models from Meta for speech and text translation, including SeamlessM4T, SeamlessExpre… | 71 | 11842 | active |
| ludwig-ai/ludwig Ludwig is a declarative, low-code deep learning framework for training, fine-tuning, and deploying AI models — from LLMs to tabular, image,… | 99 | 11745 | active |
| debpalash/VoiceStudio VoiceStudio is an open-source, fully-local desktop application (built with Tauri and Python) that provides voice cloning, voice design, vid… | 80 | 11737 | active |
| pestphp/pest Pest is an elegant PHP testing framework built on top of PHPUnit, offering a functional test API with expressive expect() assertions, datas… | 95 | 11683 | active |
| cocoindex-io/cocoindex CocoIndex is an open-source incremental data framework for AI, with a Rust engine and a declarative Python API that keeps sources (files, S… | 82 | 11409 | active |
| UI-TARS UI-TARS is ByteDance's open-source multimodal AI agent stack, comprising Agent TARS (a CLI/Web UI multimodal agent that operates terminals,… | 49 | 11389 | active |
| 0x4m4/hexstrike-ai HexStrike AI is an MCP server that bridges LLM agents (Claude, GPT, Copilot) with 150+ cybersecurity tools for autonomous penetration testi… | 61 | 11381 | active |
| salesforce/LAVIS LAVIS is a Python library from Salesforce AI Research providing a unified toolkit for language-vision (multimodal) intelligence, including … | 61 | 11262 | active |
| ifixai-ai/iFixAi iFixAi is an open-source CLI diagnostic tool that independently audits AI agents for misalignment, hallucination, manipulation, deception, … | 81 | 11173 | active |
| The-Pocket/PocketFlow Pocket Flow is a minimalist 100-line LLM framework in Python with zero dependencies, modeling LLM applications as a graph of nodes connecte… | 54 | 11135 | active |
| bytebot-ai/bytebot Bytebot is a self-hosted, open-source AI desktop agent that operates a full containerized Linux desktop, using screen vision, mouse, and ke… | 10 | 11089 | active |
| TEN-framework/ten-framework TEN is an open-source framework for building real-time multimodal conversational AI agents, with a focus on low-latency voice assistants. I… | 85 | 11082 | active |
| MemTensor/MemOS MemOS is a memory operating system for LLMs and AI agents that unifies storing, retrieving, and managing long-term, multi-modal memory thro… | 85 | 11012 | active |
| ValueCell-ai/valuecell ValueCell is a community-driven, multi-agent platform for financial applications, providing AI investment agents for stock selection, resea… | 60 | 11005 | active |
| Lightricks/LTX-Video Official repository for LTX-Video, a DiT-based open-weights video generation model from Lightricks that generates high-fidelity video (up t… | 48 | 10907 | active |
| Mail-0/Zero Zero (Mail0) is an open-source, self-hostable email client that unifies multiple providers like Gmail and Outlook into one privacy-first in… | 49 | 10784 | active |
| ChatGPTBox-dev/chatGPTBox A browser extension that deeply integrates ChatGPT into your browsing experience across Chrome, Edge, Firefox, Safari, and Android. It prov… | 93 | 10754 | active |
| OpenVINO OpenVINO is an open-source toolkit from Intel for optimizing and deploying deep learning inference across CPU, GPU, and NPU hardware. It su… | 95 | 10740 | stable |
| facebookresearch/xformers xFormers is a PyTorch-based library of hackable, optimized Transformer building blocks with custom CUDA kernels for fast, memory-efficient … | 88 | 10542 | active |
| VoltAgent/voltagent VoltAgent is an open-source TypeScript framework for building production-ready AI agents with memory, tools, RAG, guardrails, MCP, voice, a… | 80 | 10425 | active |
| sigoden/aichat AIChat is an all-in-one command-line LLM client written in Rust that connects to 20+ providers including OpenAI, Claude, Gemini, and Ollama… | 63 | 10396 | active |
| niedev/RTranslator RTranslator is a free, open-source, offline real-time translation app for Android that runs speech recognition (Whisper) and translation (M… | 85 | 10355 | active |
| OthersideAI/self-operating-computer A Python framework that lets multimodal LLMs operate a computer by viewing the screen and issuing mouse and keyboard actions to reach a sta… | 48 | 10291 | active |
| Astrid Astrid is a portable, capability-secure operating system for composable software, where every component runs as a sealed WebAssembly capsul… | 80 | 10273 | active |
| Kuberwastaken/claurst Claurst is an open-source, multi-provider terminal coding agent written in Rust, originally a clean-room reimplementation of Claude Code. I… | 79 | 10270 | active |
| snakers4/silero-vad Silero VAD is a pre-trained, enterprise-grade Voice Activity Detector model available via PyPI, runnable with PyTorch or ONNX Runtime. It d… | 86 | 10061 | stable |
| LaurieWired/GhidraMCP GhidraMCP is a Model Context Protocol server implemented as a Ghidra plugin that exposes Ghidra's reverse engineering tools to LLM clients.… | 34 | 9865 | active |
| StarTrail-org/PixelRAG PixelRAG is a Python library and hosted service for visual retrieval-augmented generation: it renders web pages and documents into screensh… | 76 | 9742 | active |
| microsoft/UFO UFO³ is Microsoft's open-source framework for LLM-powered GUI agents that automate Windows applications and orchestrate workflows across mu… | 92 | 9564 | active |
| langchain-ai/local-deep-researcher A fully local web research assistant that runs any LLM via Ollama or LMStudio to iteratively search the web, summarize findings, identify k… | 66 | 9319 | active |
| coaidev/coai CoAI.Dev is a self-hostable, multi-tenant AI platform combining a ChatGPT-style chat UI with an enterprise-grade unified LLM gateway suppor… | 56 | 9295 | active |
| lipku/LiveTalking LiveTalking is an open-source real-time interactive streaming digital human engine that drives a talking-head avatar from text or audio wit… | 89 | 9238 | active |
| higress-group/higress Higress is a CNCF Sandbox, cloud-native AI-native API gateway built on Istio and Envoy, extensible with Wasm plugins written in Go, Rust, o… | 98 | 9196 | active |
| QwenAudio/SenseVoice SenseVoice is an open-source speech foundation model (SenseVoiceSmall) providing multilingual ASR, spoken language identification, speech e… | 88 | 9151 | active |
| kyutai-labs/pocket-tts Pocket TTS is a lightweight 100M-parameter text-to-speech model and Python library from Kyutai that runs efficiently on CPUs without a GPU.… | 83 | 9135 | active |
| crynta/terax-ai Terax is a lightweight (~7 MB) open-source desktop application that combines a GPU-rendered terminal, code editor, file explorer, git sourc… | 80 | 9107 | active |
| studio-dots-ai/dots.ocr dots.ocr is a 1.7B-parameter vision-language model for multilingual document layout parsing, converting documents into structured output wi… | 51 | 9090 | active |
| miurla/morphic Morphic is an open-source AI-powered search engine that generates grounded, cited answers with a generative UI that renders rich inline com… | 91 | 9067 | active |
| NVIDIA/garak garak is a command-line LLM vulnerability scanner that probes large language models for failures like hallucination, data leakage, prompt i… | 91 | 9033 | active |
| OpenSPG/KAG KAG (Knowledge Augmented Generation) is a Python framework built on the OpenSPG engine and large language models for logical form-guided re… | 49 | 9018 | active |
| kangarooking/cangjie-skill Cangjie Skill is a Python-based tool that distills methodologies from high-value content like books, long-form videos, and podcasts into ex… | 80 | 9016 | active |
| dusty-nv/jetson-inference A C++/Python DNN inference library and tutorial guide ('Hello AI World') for deploying deep learning vision models on NVIDIA Jetson devices… | 44 | 8969 | stable |
| cookieY/Yearning Yearning is a self-hosted web-based SQL audit platform for MySQL, providing audit tickets with approval workflows, automated syntax checkin… | 79 | 8964 | active |
| anthropics/claude-code-action A GitHub Action that runs Claude Code on pull requests and issues, answering questions, reviewing code, and implementing changes triggered … | 82 | 8729 | active |
| justlovemaki/AIClient2API AIClient2API is a self-hosted Node.js proxy that simulates client-only LLM service requests (Antigravity, Codex, Grok, Kiro, Gemini CLI, et… | 81 | 8697 | active |
| companion-inc/feynman Feynman is an open-source AI research agent that reads papers, searches the web, writes cited research drafts, plans experiments, and ranks… | 77 | 8588 | active |
| hexgrad/kokoro An inference library for Kokoro-82M, an open-weight text-to-speech model with 82 million parameters that delivers quality comparable to lar… | 36 | 8570 | active |
| lastmile-ai/mcp-agent mcp-agent is a Python framework for building AI agents on top of the Model Context Protocol (MCP) using simple, composable workflow pattern… | 52 | 8519 | active |
| LC044/WeChatMsg WeChatMsg (留痕/MemoTrace) is a desktop application built with PyQt that extracts, exports, and preserves WeChat chat history on a user's own… | 58 | 42006 | maintenance |
| TeamWiseFlow/xiaobei Xiaobei is an open-source multi-agent system that automates social media marketing and customer acquisition for solo entrepreneurs and smal… | 90 | 8463 | active |
| thesysdev/openui OpenUI is an open-source, renderer-agnostic Generative UI framework built around OpenUI Lang, a compact streaming-first DSL that lets LLM a… | 66 | 8463 | active |
| QwenLM/Qwen-Image Qwen-Image is a 20B MMDiT image generation foundation model from the Qwen team, with strong complex text rendering (especially Chinese) and… | 48 | 8265 | active |
| EstrellaXD/Auto_Bangumi AutoBangumi is a self-hosted, RSS-based automated anime downloading and organizing tool. It parses RSS feeds from sites like Mikan Project,… | 96 | 8226 | active |
| zilliztech/deep-searcher DeepSearcher is an open-source deep research tool that combines LLMs (DeepSeek, OpenAI, Claude, Qwen, etc.) with vector databases like Milv… | 35 | 8224 | active |
| Ucas-HaoranWei/GOT-OCR2.0 Official implementation of GOT-OCR2.0, a unified end-to-end vision-language model for general OCR that converts images of text, documents, … | 25 | 8216 | active |
| n4ze3m/page-assist Page Assist is an open-source browser extension that adds a sidebar and web UI for interacting with locally running AI models like Ollama f… | 93 | 8181 | active |
| GetStream/Vision-Agents An open-source Python framework by Stream for building low-latency real-time voice and video AI agents. It provides 35+ provider plugins (O… | 84 | 8100 | active |
| leptonai/search_with_lepton A demo application for building a conversational AI search engine (Perplexity-style) in under 500 lines of code, combining LLMs with search… | 10 | 8070 | active |
| NullClaw NullClaw is an autonomous AI assistant/agent runtime written in Zig, distributed as a tiny static binary (~678 KB, ~1 MB RAM, <2 ms startup… | 75 | 8052 | active |
| suno-ai/bark Bark is Suno's open-source transformer-based text-to-audio model that generates highly realistic multilingual speech, music, background noi… | 30 | 39249 | maintenance |
| open-pencil/open-pencil OpenPencil is an open-source, AI-native design editor that opens and writes native Figma (.fig) files, with built-in AI chat that can creat… | 81 | 8003 | active |
| SciPhi-AI/R2R R2R is a production-ready AI retrieval system implementing agentic Retrieval-Augmented Generation (RAG) with a RESTful API. It provides sta… | 50 | 7978 | active |
| pinokiocomputer/pinokio Pinokio is a desktop application that acts as a one-click launcher and browser for open-source AI apps, letting users discover, install, ru… | 91 | 7878 | active |
| evidentlyai/evidently Evidently is an open-source Python framework for evaluating, testing, and monitoring ML and LLM-powered systems, with 100+ built-in metrics… | 89 | 7849 | active |
| wang-xinyu/tensorrtx A C++ collection of popular deep learning networks (YOLO variants, ResNet, MobileNet, Swin Transformer, OCR models, and more) implemented f… | 76 | 7827 | active |
| Blaizzy/mlx-audio MLX-Audio is a Python library built on Apple's MLX framework for fast text-to-speech (TTS), speech-to-text (STT), and speech-to-speech (STS… | 88 | 7793 | active |
| Azure-Samples/azure-search-openai-demo A reference sample application implementing the Retrieval-Augmented Generation (RAG) pattern on Azure, combining Azure AI Search for docume… | 95 | 7746 | active |
| MeiGen-AI/InfiniteTalk InfiniteTalk is an open-source model and framework for unlimited-length audio-driven talking video generation, supporting both image-to-vid… | 55 | 7700 | active |
| meituan-longcat/LongCat-Video LongCat-Video is a 13.6B-parameter foundational video generation model from Meituan that unifies text-to-video, image-to-video, and video-c… | 54 | 7665 | active |
| logancyang/obsidian-copilot Copilot for Obsidian is an Obsidian community plugin that adds AI chat and agent capabilities to your note vault, integrating opencode, Cla… | 93 | 7628 | active |
| maximhq/bifrost Bifrost is a high-performance, open-source AI gateway written in Go that unifies access to 23+ LLM providers (OpenAI, Anthropic, AWS Bedroc… | 83 | 7587 | active |
| SkyworkAI/SkyReels-V2 SkyReels-V2 is an open-source infinite-length film/video generative model using an AutoRegressive Diffusion-Forcing architecture, released … | 48 | 7462 | 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… | 25 | 7425 | active |
| QuivrHQ/MegaParse MegaParse is a Python library that parses PDFs, Word, PowerPoint, Excel, CSV, and text documents into LLM-friendly formats with a focus on … | 29 | 7413 | active |
| flyteorg/flyte Flyte is an open-source workflow orchestration platform for coordinating data, ML models, and AI agents at scale, authored in pure Python a… | 95 | 7245 | active |
| Zyphra/Zonos Zonos-v0.1 is an open-weight text-to-speech model trained on over 200k hours of multilingual speech, with a Python library for inference. I… | 24 | 7244 | active |
| rikkahub/rikkahub RikkaHub is a native Android LLM chat client built with Kotlin and Jetpack Compose that supports switching between multiple AI providers su… | 83 | 7196 | 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… | 88 | 7172 | active |
| JefferyHcool/BiliNote BiliNote is an open-source AI video note-taking application that turns video links from Bilibili, YouTube, Douyin, and local files into str… | 86 | 7169 | active |