function: llm-inference
3362 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| jordan-gibbs/hyperresearch Hyperresearch is a Python CLI harness that turns Claude Code into a deep research agent running a 16-step adversarially-audited pipeline. I… | 78 | 1846 | active |
| NVIDIA-AI-Blueprints/video-search-and-summarization NVIDIA's GPU-accelerated AI Blueprint reference architecture for building video analytics agents that search, summarize, and reason over li… | 83 | 1845 | active |
| Tencent-Hunyuan/HunyuanVideo-I2V HunyuanVideo-I2V is Tencent's open-source image-to-video generation framework built on the HunyuanVideo diffusion model, providing PyTorch … | 54 | 1840 | active |
| fastino-ai/GLiNER2 GLiNER2 is a Python library for schema-based information extraction and text classification, supporting named entity recognition, structure… | 85 | 1837 | active |
| superdesigndev/superdesign SuperDesign is an open-source AI design agent that lives inside your IDE (VS Code, Cursor, Windsurf, Claude Code) and generates UI mockups,… | 59 | 6914 | maintenance |
| AgiBot X1 The inference module of the open-source AgiBot X1 humanoid robot software stack, providing model inference, platform drivers, and simulatio… | 28 | 1834 | active |
| Zheng-Chong/CatVTON CatVTON is a lightweight diffusion model for virtual try-on that swaps clothing onto a person image using a concatenation-based architectur… | 40 | 1830 | active |
| boundless-large-model/boundless-world-model Boundless-World-Model (BWM) is a physically consistent, action-conditioned video world model built on Wan2.2-TI2V-5B that acts as a low-cos… | 59 | 1829 | active |
| OpenAgentPlatform/Dive Dive is an open-source MCP host desktop application that connects to any LLM supporting function calling, including ChatGPT, Anthropic, Oll… | 80 | 1826 | active |
| wzc520pyfm/ant-design-x-vue A Vue implementation of Ant Design X, providing a component library for building AI-driven chat and copilot interfaces based on the RICH in… | 76 | 1825 | active |
| rcortx/kiwiq KiwiQ is a production-grade multi-agent orchestration platform in Python that lets you define AI workflows as JSON/Python graph schemas com… | 49 | 1822 | active |
| xenodium/agent-shell agent-shell is an Emacs Lisp package that provides a native Emacs buffer interface for interacting with LLM coding agents (Claude Code, Ope… | 62 | 1821 | active |
| OpenBMB/StaffDeck StaffDeck is an open-source enterprise platform for building and managing AI-powered digital employees that codify professional experience,… | 80 | 1819 | active |
| OpenImagingLab/FlashVSR FlashVSR is a one-step diffusion-based streaming video super-resolution framework that runs at ~17 FPS for 768x1408 video on a single A100 … | 61 | 1817 | active |
| tuya/TuyaOpen TuyaOpen is an open-source, cross-platform C/C++ SDK and IoT OS for building AI-agent hardware on Tuya T-series MCUs, ESP32, Beken, LN882H,… | 87 | 1816 | active |
| whotto/Video_note_generator A Python tool that converts video URLs into polished Xiaohongshu (Little Red Book) notes and blog articles. It downloads videos, transcribe… | 43 | 1812 | active |
| triple-mu/YOLOv8-TensorRT A library for running YOLOv8 inference accelerated with NVIDIA TensorRT, supporting detection, segmentation, pose estimation, oriented boun… | 75 | 1807 | active |
| Stability-AI/stable-fast-3d Stable Fast 3D (SF3D) is Stability AI's open-source model that reconstructs a textured, UV-unwrapped 3D mesh from a single input image in a… | 24 | 1800 | active |
| zi-yue-1129/DATAGEN DATAGEN is an AI-powered multi-agent research and data analysis platform built with LangChain, LangGraph, and OpenAI GPT models. It automat… | 67 | 1797 | active |
| gnipbao/story-to-handdrawn-video A Remotion-based renderer plus distributable agent skill that converts Chinese story text or ordered images into 3:4 vertical hand-drawn di… | 56 | 1792 | active |
| jd-opensource/JoyAI-Video-Edit JoyAI-Video-Edit is a real-time, instruction-guided video editing system that applies natural-language edits to live or uploaded video stre… | 57 | 1788 | active |
| xyTom/snippai Snippai is an AI-powered snipping tool that captures screenshots and uses AI to extract structured content such as LaTeX formulas, text, ta… | 89 | 1786 | active |
| beam-cloud/beta9 Beam (beta9) is an open-source serverless runtime for AI workloads, providing GPU inference endpoints, isolated sandboxes for running untru… | 89 | 1766 | active |
| a5c-ai/babysitter Babysitter is an npm-distributed CLI and runtime that enforces deterministic, step-by-step process control on AI coding agents across 12 su… | 75 | 1765 | active |
| character-ai/Ovi Ovi is a video-plus-audio generation model from Character AI that simultaneously generates synchronized video and audio from text or text+i… | 40 | 1756 | active |
| HITsz-TMG/VideoClaw VideoClaw is an AI director system that turns a one-line idea or story synopsis into a fully automated video production pipeline, covering … | 67 | 1755 | active |
| run-llama/rags A Streamlit web app that lets users build a RAG (retrieval-augmented generation) pipeline over their data using natural language instructio… | 27 | 6549 | maintenance |
| LLM Sherpa LLM Sherpa is a Python client library providing APIs for layout-aware PDF and document parsing to feed LLM applications, backed by the open… | 18 | 1749 | active |
| deepseek-ai/TileKernels TileKernels is a Python library of optimized GPU kernels for LLM operations, written in the TileLang DSL. It provides kernels for MoE routi… | 49 | 1748 | active |
| skalesapp/skales Skales is a personal AI agent desktop and mobile application that runs locally on Windows, macOS, Linux, Android, and iOS, executing multi-… | 82 | 1745 | active |
| dongsheng123132/u-claw U-Claw is an open-source portable USB skeleton and installer toolkit that packages the OpenClaw AI assistant framework (plus Claude Code/Co… | 82 | 1743 | active |
| VAST-AI-Research/UniRig UniRig is the official implementation of a SIGGRAPH 2025 framework that automatically rigs 3D models by predicting skeletons and skinning w… | 58 | 1733 | active |
| aklivity/zilla Zilla is a stateless, multi-protocol gateway for event-driven applications and AI agents, exposing Kafka and MQTT over HTTP, SSE, gRPC, MQT… | 99 | 1731 | active |
| lifan0127/ai-research-assistant Aria is a Zotero plugin that brings GPT-powered AI assistance to reference management, letting researchers chat with their library items, P… | 38 | 1727 | active |
| ginlix-ai/LangAlpha LangAlpha is an open-source agentic AI harness for financial market research and investment decision support, inspired by code-agent harnes… | 81 | 1720 | active |
| icebear0828/codex-proxy A lightweight local proxy service that exposes ChatGPT Codex Desktop's Responses API through standard OpenAI, Anthropic, Gemini, and Ollama… | 82 | 1714 | active |
| arabold/docs-mcp-server A self-hosted MCP server that indexes documentation from websites, GitHub, npm, PyPI, and local files so AI coding assistants can query up-… | 82 | 1707 | active |
| swark-io/swark Swark is a VS Code extension that automatically generates architecture diagrams from source code using large language models, integrated di… | 29 | 1695 | active |
| mlrun/mlrun MLRun is an open-source MLOps and AI orchestration framework for building, training, deploying, and monitoring machine learning and generat… | 96 | 1694 | active |
| mateaix/matecloud MateCloud is a Java-based microservices scaffold built on Spring Boot 4, Spring Cloud 2025, Spring Cloud Alibaba, and Dubbo 3, offering gat… | 83 | 1693 | active |
| trailofbits/buttercup Buttercup is a Cyber Reasoning System (CRS) developed by Trail of Bits for the DARPA AI Cyber Challenge that automatically finds and patche… | 56 | 1693 | active |
| kenn-io/roborev roborev is a Go-based continuous code review tool for AI coding agents that reviews every commit in the background via git hooks and surfac… | 78 | 1691 | active |
| kijai/ComfyUI-FramePackWrapper A ComfyUI custom node wrapper for FramePack, enabling next-frame video generation from images using HunyuanVideo-based diffusion models. It… | 47 | 1685 | active |
| Datus-ai/Datus-agent Datus is an open-source (Apache-2.0) AI data engineering agent delivered primarily as a Python CLI, with a VS Code/Cursor extension and opt… | 84 | 1682 | active |
| absadiki/subsai Subs AI is a subtitles generation tool available as a Web-UI, CLI, and Python package, powered by OpenAI's Whisper and its variants (faster… | 66 | 1681 | active |
| Orkas-AI/Orkas Orkas is an open-source, local-first multi-agent desktop application where a Commander LLM plans goals and dispatches specialist sub-agents… | 81 | 1678 | active |
| mattpocock/evalite Evalite is a TypeScript-native eval runner for testing LLM-powered applications, built on Vitest with a local dev server UI for exploring o… | 60 | 1675 | active |
| Rohithgilla12/data-peek data-peek is a minimal, fast, keyboard-first SQL client desktop application built with Electron and TypeScript for quickly querying and exp… | 81 | 1674 | active |
| classroomio/classroomio ClassroomIO is an open-source learning management system (LMS) for companies to run employee compliance training, customer education, and p… | 72 | 1671 | active |
| Gen-Verse/MMaDA MMaDA is an open-source family of multimodal large diffusion language models that unify textual reasoning, multimodal understanding, and te… | 49 | 1671 | active |
| mims-harvard/ToolUniverse ToolUniverse is a Python SDK and MCP server that aggregates a large collection of scientific tools (APIs, databases, local ML and cheminfor… | 82 | 1670 | active |
| Picsart-AI-Research/StreamingT2V StreamingT2V is a research codebase (CVPR 2025) implementing an autoregressive technique that turns short text-to-video diffusion models li… | 31 | 1629 | active |
| Lynpoint/CyberVerse CyberVerse is an open-source, self-hosted framework for building real-time, voice-first AI agents with optional digital-human video (talkin… | 63 | 1628 | active |
| Fantasy-AMAP/fantasy-talking FantasyTalking is a research codebase and model for generating realistic talking portrait videos from a single image and an audio clip, bui… | 48 | 1628 | active |
| difyz9/ytb2bili ytb2bili is a self-hosted video workflow application that automates downloading videos from YouTube, generating and translating subtitles, … | 79 | 1621 | active |
| juliye2025/evil-read-arxiv A collection of Claude Code / OpenAI Codex skills plus a Next.js web app that automates research paper discovery, analysis, and note-taking… | 57 | 1615 | active |
| stanford-oval/WikiChat WikiChat is a retrieval-augmented generation (RAG) framework that grounds LLM chatbot responses in a corpus (Wikipedia by default) to reduc… | 47 | 1615 | active |
| tickernelz/opencode-mem An OpenCode plugin that gives AI coding agents persistent memory across sessions using an embedded local Turso/libSQL vector database. It a… | 82 | 1612 | active |
| Pinvou/pinvou-agent Pinvou Agent is an open-source, local-first desktop AI agent workspace built with Rust and Tauri that combines chat, file operations, perso… | 66 | 1604 | active |
| LYiHub/mad-professor-public A desktop AI companion application for reading academic papers, built with PyQt6. It combines PDF parsing and translation, RAG-based retrie… | 27 | 1604 | active |
| getnao/nao nao is an open-source framework for building and deploying analytics agents that answer natural-language questions about data. It combines … | 82 | 1603 | active |
| Agents365-ai/video-podcast-maker An agent skill/plugin that turns a plain-language topic into a 4K narrated video podcast, combining research, script generation, multi-engi… | 79 | 1600 | active |
| SAGAR-TAMANG/friday-tony-stark-demo F.R.I.D.A.Y. is a Tony Stark-inspired voice AI assistant consisting of a FastMCP server exposing tools (web search, news, system info) and … | 55 | 1599 | active |
| theopenco/llmgateway LLM Gateway is an open-source API gateway for large language models that sits between applications and 40+ LLM providers (OpenAI, Anthropic… | 86 | 1598 | active |
| bubbuild/bub Bub is a small Python runtime for building AI agents that operate in shared environments alongside humans. It uses a hook-first architectur… | 85 | 1597 | active |
| semperai/amica Amica is an open-source web application for conversing with customizable 3D characters through voice chat, speech recognition, and vision. … | 32 | 1594 | active |
| ssnangua/ColorTxt ColorTxt is a local desktop novel reader for TXT and common ebook formats (epub, mobi, pdf, etc.) that colorizes content with custom highli… | 80 | 1592 | active |
| datagouv/datagouv-mcp The official Model Context Protocol (MCP) server for data.gouv.fr, the French national open data platform. It lets AI chatbots like Claude,… | 78 | 1589 | active |
| Jamailar/Beav Beav (formerly RedBox) is a local-first AI content operations workbench for social media creators, combining a desktop app and a Chrome/Edg… | 81 | 1585 | active |
| steedos/steedos-platform Steedos Platform is an open-source, metadata-driven low-code platform for building enterprise applications (CRMs, ERPs, approval workflows)… | 89 | 1575 | active |
| IDEA-Research/Rex-Omni Rex-Omni is a 3B-parameter multimodal large language model that unifies object detection, OCR, pointing, keypoint detection, and visual pro… | 47 | 1570 | active |
| lucasastorian/llmwiki An open-source implementation of Andrej Karpathy's LLM Wiki concept: a self-maintaining personal knowledge base where an LLM (connected via… | 57 | 1567 | active |
| oxylabs/browser-agent-py A Python SDK for Oxylabs AI Studio's Browser Agent, a cloud service that automates real-user browsing tasks (clicking, typing, scrolling, s… | 51 | 1566 | active |
| vibevoice-community/VibeVoice VibeVoice is a community-maintained fork of Microsoft's long-form conversational text-to-speech model, generating expressive multi-speaker … | 60 | 1563 | active |
| feenkcom/gtoolkit Glamorous Toolkit is the Moldable Development environment built on Pharo/Smalltalk, providing an integrated IDE with thousands of contextua… | 95 | 1562 | active |
| fabro-sh/fabro Fabro is an open-source workflow orchestration engine that runs AI coding agents as version-controlled workflow graphs defined in Graphviz … | 77 | 1561 | active |
| shrimbly/node-banana Node Banana is an open-source, node-based visual workflow editor for building AI media generation pipelines. Users connect nodes on an infi… | 81 | 1560 | active |
| pipecat-ai/smart-turn Smart Turn is an open-source, audio-native turn detection model that decides when a voice agent should respond to human speech, using proso… | 49 | 1559 | active |
| shiwenwen/hope-agent Hope Agent is a local-first, cross-device desktop AI assistant built with Rust and Tauri that features long-term memory, autonomous goal pu… | 82 | 1555 | active |
| Enemyx-net/VibeVoice-ComfyUI A ComfyUI custom node integration for Microsoft's VibeVoice text-to-speech model, providing single and multi-speaker voice synthesis with v… | 53 | 1554 | active |
| ZeyueT/AudioX AudioX is a unified multimodal framework for anything-to-audio generation, producing audio and music conditioned on text, video, image, or … | 52 | 1552 | active |
| RightNow-AI/autokernel AutoKernel is an open-source autoresearch pipeline that takes any PyTorch model, profiles it to find GPU kernel bottlenecks, extracts them … | 48 | 1548 | active |
| roncoo/roncoo-education Roncoo Education (领课教育系统) is an open-source online education platform built with a Spring Cloud Alibaba microservices backend and Vue 3/Nux… | 68 | 1546 | active |
| RTGS2017/NagaAgent NagaAgent is a desktop AI personal assistant framework with an anime (Live2D) virtual character, built in Python with an Electron front end… | 83 | 1542 | active |
| GitHamza0206/simba Simba is an open-source, production-ready customer service assistant and knowledge management system built around a fully customizable RAG … | 62 | 1539 | active |
| zenstory-ai/drama-skills A collection of ten agent skills for AI short-drama and comic-drama production, covering scripts, visual assets, storyboards, image/video p… | 80 | 1538 | active |
| feremabraz/bloomberg-terminal A Bloomberg Terminal clone built with Next.js 15, React 19, and TypeScript that provides real-time financial market data visualization in a… | 51 | 1534 | active |
| NanoNets/docstrange DocStrange is a Python library and tool that converts documents (PDF, DOCX, PPTX, XLSX, images, URLs) into Markdown, JSON, CSV, or HTML usi… | 40 | 1534 | active |
| zzet/gortex Gortex is a high-performance code-intelligence engine that indexes codebases into a persistent knowledge graph using tree-sitter AST analys… | 77 | 1530 | active |
| video-db/Director Director is a Python framework for building AI video agents that reason over complex video tasks like search, editing, compilation, and gen… | 41 | 1525 | active |
| met4citizen/TalkingHead A JavaScript library for real-time lip-synced talking avatars, rendering full-body 3D characters in the browser. It supports text-to-speech… | 67 | 1524 | active |
| Zhengqbbb/cz-git cz-git is a highly customizable, lightweight Commitizen adapter for generating standardized Conventional Commits git commit messages, with … | 95 | 1523 | active |
| tin2tin/Pallaidium Pallaidium is a free, open-source generative AI movie studio implemented as a Blender add-on integrated into the Video Sequence Editor (VSE… | 75 | 1523 | active |
| bytedance/SALMONN SALMONN is a family of open-source multi-modal large language models from ByteDance and Tsinghua that unify speech, audio, music, and video… | 73 | 1522 | active |
| OpenOSINT/OpenOSINT OpenOSINT is an AI-powered OSINT framework offering 19 investigation tools behind a natural-language agent, usable as an interactive REPL, … | 81 | 1521 | active |
| DocumindHQ/documind Documind is an open-source Node.js library that uses AI/LLMs to extract structured JSON data from PDFs and other documents based on customi… | 33 | 1520 | active |
| kyutai-labs/hibiki Hibiki is a decoder-only model for streaming (simultaneous) speech-to-speech translation, built on the multistream Moshi architecture. It p… | 28 | 1512 | active |
| akto-api-security/akto Akto is an open-source API and AI security platform that discovers and inventories APIs, AI agents, MCP servers, and LLM usage, then contin… | 94 | 1511 | active |
| golemcloud/golem Golem is an open-source durable agent runtime and serverless platform for running WebAssembly components in a distributed cloud environment… | 89 | 1510 | active |
| HiDream-ai/HiDream-O1-Image HiDream-O1-Image is an open-weights 8B image generation foundation model built on a Pixel-level Unified Transformer (UiT) that natively enc… | 53 | 1510 | active |