function: llm-inference
3362 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| JoshuaC215/agent-service-toolkit A full toolkit for building and running an AI agent service using LangGraph, FastAPI, and Streamlit. It provides a template including a Lan… | 68 | 4443 | active |
| ragapp/ragapp RAGapp is a self-hosted, Docker-deployable application for building Agentic RAG chatbots, configurable through an admin UI similar to OpenA… | 27 | 4442 | active |
| pydantic/logfire Pydantic Logfire is an AI observability platform built on OpenTelemetry that traces LLM calls, agent runs, and application telemetry in one… | 87 | 4441 | active |
| xlite-dev/lite.ai.toolkit A lightweight C++ toolkit providing unified APIs for 100+ pre-trained AI models across inference backends like ONNX Runtime, MNN, TensorRT,… | 74 | 4427 | active |
| gptme/gptme gptme is a free, open-source personal AI agent that runs in the terminal, equipped with local tools for shell execution, code writing, file… | 97 | 4399 | active |
| jupyterlab/jupyter-ai Jupyter AI is an open-source JupyterLab extension that connects agentic AI assistants to computational notebooks via the Agent Client Proto… | 97 | 4382 | active |
| intuitem/ciso-assistant-community CISO Assistant is an open-source, self-hostable GRC (Governance, Risk, and Compliance) platform covering risk management, compliance and au… | 90 | 4376 | active |
| microsoft/PyRIT PyRIT is Microsoft's open-source Python framework for identifying security and safety risks in generative AI systems. It provides automatio… | 88 | 4361 | active |
| dramaclaw/dramaclaw DramaClaw is a self-hosted, general-purpose AIGC video engine that turns scripts into finished films through a single pipeline covering sto… | 81 | 4355 | active |
| antvis/mcp-server-chart A Model Context Protocol (MCP) server, written in TypeScript, that exposes tools for generating 26+ chart types using the AntV visualizatio… | 76 | 4341 | active |
| cs-lazy-tools/ChatGPT-On-CS An open-source LLM-powered intelligent customer-service tool that connects to e-commerce and social platforms like WeChat, Pinduoduo, Qiann… | 54 | 4311 | active |
| httprunner/httprunner HttpRunner (hrp) is an open-source, Go-based all-in-one testing framework for API testing (HTTP/HTTP2/WebSocket/RPC), load testing, and mul… | 48 | 4295 | active |
| Tencent-Hunyuan/HunyuanDiT Hunyuan-DiT is Tencent's open-source diffusion transformer model for text-to-image generation with fine-grained Chinese language understand… | 49 | 4291 | active |
| ThilinaRajapakse/simpletransformers Simple Transformers is a Python library built on Hugging Face Transformers that lets users train, fine-tune, and evaluate Transformer model… | 61 | 4254 | active |
| collabora/WhisperLive WhisperLive is a nearly-live speech-to-text application built on OpenAI's Whisper, serving real-time transcription over WebSocket and REST … | 86 | 4241 | active |
| kevin2li/PDF-Guru PDF Guru Anki is a cross-platform desktop and mobile application that combines a comprehensive PDF toolbox with deep Anki integration, conv… | 30 | 4217 | active |
| ArcReel/ArcReel ArcReel is an open-source, self-hosted AI video production workspace that turns novels, scripts, or product material into characters, scene… | 82 | 4211 | active |
| fatihak/InkyPi InkyPi is an open-source E-Ink display application that runs on a Raspberry Pi and is controlled through a web interface. It supports plugi… | 66 | 4184 | active |
| open-legal-products/mike Mike is an open-source, self-hostable legal AI platform combining a Next.js frontend and Express backend for document review, drafting, and… | 79 | 4157 | active |
| ministackorg/ministack MiniStack is a free, MIT-licensed local AWS emulator that mimics 60+ AWS services (S3, SQS, SNS, DynamoDB, Lambda, EC2, RDS, ElastiCache, E… | 77 | 4140 | active |
| VectorSpaceLab/OmniGen2 OmniGen2 is an open-source unified multimodal generation model supporting text-to-image generation, instruction-guided image editing, and i… | 52 | 4112 | active |
| ericc-ch/copilot-api A reverse-engineered proxy that exposes the GitHub Copilot API as OpenAI and Anthropic compatible endpoints, letting any OpenAI/Anthropic-c… | 49 | 4106 | active |
| CSGHub CSGHub is an open-source, self-hostable platform for managing the full lifecycle of LLM assets including models, datasets, spaces, and agen… | 91 | 4097 | active |
| zhukunpenglinyutong/desktop-cc-gui Desktop CC GUI (ccgui) is an open-source multi-engine AI coding desktop client built with Tauri 2, React 19, TypeScript, and Rust. It wraps… | 78 | 4092 | active |
| groupultra/telegram-search A self-hostable tool that exports, backs up, and indexes Telegram chat history into a database (PGlite or PostgreSQL) with tokenization and… | 83 | 4078 | active |
| QwenLM/Qwen2.5-Omni Qwen2.5-Omni is an end-to-end multimodal model from Alibaba's Qwen team that understands text, images, audio, and video, and generates stre… | 31 | 4074 | active |
| lllyasviel/Paints-UNDO Paints-UNDO is a family of deep learning models that take an image as input and generate the step-by-step drawing sequence (sketching, inki… | 40 | 4067 | active |
| umlx5h/LLPlayer LLPlayer is a Windows media player built for language learning, featuring dual subtitles, AI-generated subtitles via Whisper ASR, real-time… | 78 | 4049 | active |
| MOSS-TTS MOSS-TTS-Nano is an open-source 0.1B-parameter multilingual speech generation (TTS) model from MOSI.AI and the OpenMOSS team, designed for … | 57 | 4031 | active |
| javahuang/SurveyKing SurveyKing is a self-hosted, open-source (MIT) survey, exam, and question-bank practice platform built with Java/Spring Boot and React, dep… | 67 | 3991 | active |
| OSU-NLP-Group/HippoRAG HippoRAG is a Python RAG framework inspired by human long-term memory that combines LLMs, knowledge graphs, and Personalized PageRank to in… | 59 | 3967 | active |
| BenedictKing/ccx CCX is a self-hosted AI API proxy and protocol translation gateway written in Go that unifies access to Claude, OpenAI Chat/Images/Embeddin… | 76 | 3963 | active |
| AnswerDotAI/RAGatouille RAGatouille is a Python library that makes it easy to use and train state-of-the-art late-interaction retrieval models like ColBERT in any … | 26 | 3953 | active |
| mushan0x0/AI0x0.com AI 0x0 is a multimodal, multi-model desktop AI assistant that lives as a floating ball on macOS and Windows, letting users invoke AI querie… | 34 | 3938 | active |
| Hacker233/resume-design Maobu Resume (猫步简历) is an open-source, free online resume builder built with Vue 3, TypeScript, Vite, Element Plus, and Pinia. It offers tw… | 61 | 3925 | active |
| Tencent-Hunyuan/Hunyuan3D-2.1 Tencent's open-source 3D asset generation model that creates high-fidelity 3D meshes with production-ready PBR materials from single images… | 40 | 3917 | active |
| claraverse-space/ClaraVerse ClaraVerse is a self-hosted, privacy-focused AI workspace that combines chat, multi-agent teams, a visual workflow builder, RAG document pr… | 80 | 3894 | active |
| mayooear/ai-pdf-chatbot-langchain A monorepo template for an AI PDF chatbot agent that ingests PDFs, stores embeddings in Supabase, and answers questions using OpenAI via La… | 10 | 16598 | maintenance |
| VectifyAI/OpenKB OpenKB is an open-source CLI tool that compiles raw documents (PDF, Word, Markdown, HTML, and more) into a structured, interlinked wiki-sty… | 76 | 3847 | active |
| zly2006/zhihu-plus-plus Zhihu++ is an open-source third-party Android client for the Chinese Q&A platform Zhihu, built in Kotlin, that removes ads, promotional pos… | 85 | 3845 | active |
| sentient-agi/OpenDeepSearch OpenDeepSearch is an open-source search tool that augments LLMs and reasoning agents with web search capabilities, aiming to match closed-s… | 26 | 3842 | active |
| shy3130/tick-stock-panel A self-hosted, zero-ops quantitative workbench for China A-share stock screening, monitoring, and backtesting, built with Python (FastAPI, … | 58 | 3817 | active |
| Atmosphere/atmosphere Atmosphere is a portable AI agent runtime for the JVM that lets a single @Agent class run across twelve AI runtimes (Spring AI, LangChain4j… | 95 | 3796 | active |
| lanqian528/chat2api A Python service that proxies ChatGPT's web interface into an OpenAI-compatible API format, supporting GPT-3.5, GPT-4/4o, O1/O3 models, GPT… | 35 | 3794 | active |
| deanxv/coze-discord-proxy A self-hosted Go service that proxies conversations to a Coze-Bot on Discord, exposing OpenAI-compatible API endpoints (v1/chat/completions… | 58 | 3787 | stable |
| didi/xiaoju-survey XIAOJUSURVEY is an open-source enterprise form builder and analytics platform for creating questionnaires, exams, polls, quizzes, and compl… | 69 | 3786 | active |
| nageoffer/ragent Ragent AI is a production-grade Java platform for building Agentic RAG applications, covering document ingestion, hybrid retrieval (vector,… | 78 | 3779 | active |
| SandAI-org/MAGI-1 MAGI-1 is an open-source autoregressive video generation model from Sand.ai, released with Apache-2.0 licensed code and weights. It generat… | 59 | 3772 | active |
| HeartMuLa/heartlib HeartMuLa is a family of open-source music foundation models that generate music conditioned on lyrics and tags with multilingual support. … | 50 | 3749 | active |
| HumanAIGC-Engineering/OpenAvatarChat OpenAvatarChat is a modular interactive digital human (talking avatar) chat application that combines ASR, LLM, TTS, and avatar rendering c… | 74 | 3723 | active |
| aiming-lab/SimpleMem SimpleMem is a Python library and MCP server that provides efficient lifelong memory for LLM agents, storing, compressing, and retrieving l… | 71 | 3720 | active |
| genmoai/mochi Mochi 1 is Genmo's open-source, state-of-the-art text-to-video generation model released under Apache 2.0, with a Python API, CLI, and Grad… | 46 | 3713 | active |
| morphik-org/morphik-core Morphik Core is an open-source, source-available multimodal retrieval engine for building RAG applications over unstructured data like PDFs… | 64 | 3708 | active |
| gadievron/raptor RAPTOR is an autonomous offensive/defensive security research framework built on top of Claude Code, chaining static analysis, binary analy… | 66 | 3672 | active |
| HazyResearch/ThunderKittens ThunderKittens is a C++/CUDA framework of tile-based primitives for writing fast deep learning GPU kernels. It embeds natively into CUDA so… | 70 | 3659 | active |
| speaches-ai/speaches Speaches is an OpenAI API-compatible self-hosted server for speech-to-text (via faster-whisper), translation, and text-to-speech (via Kokor… | 78 | 3621 | active |
| facebookresearch/sam-audio SAM-Audio is Meta's foundation model for isolating any sound in audio using text, visual, or temporal prompts. This repository provides inf… | 55 | 3612 | active |
| geekjourneyx/md2wechat-skill md2wechat is a Go-based CLI tool that converts Markdown into styled WeChat Official Account HTML, with 40+ themes, AI-generated covers and … | 81 | 3594 | active |
| shinyflvre/Mate-Engine Mate Engine is a free, open-source desktop companion (desktop pet) app that displays 3D anime-style VRM avatars on your screen with idle an… | 55 | 3586 | active |
| sligter/LandPPT LandPPT is an AI-powered presentation generation platform that turns a topic or uploaded documents (PDF, Word, Markdown, Excel, PPT) into p… | 81 | 3575 | active |
| nextlevelbuilder/goclaw GoClaw is a multi-tenant AI agent platform and gateway rebuilt from OpenClaw in Go, supporting 20+ LLM providers and 7 messaging channels f… | 74 | 3563 | active |
| Soul-AILab/SoulX-Podcast SoulX-Podcast is the official inference codebase for a text-to-speech model that generates long-form, multi-turn, multi-speaker podcast-sty… | 42 | 3535 | active |
| truera/trulens TruLens is a Python library for evaluating and tracking LLM-based applications and AI agents. It provides OpenTelemetry-native tracing of e… | 95 | 3525 | active |
| pathwaycom/bdh BDH (Dragon Hatchling) is a biologically inspired large language model architecture that bridges deep learning and neuroscience, implemente… | 54 | 3519 | active |
| langwatch/langwatch LangWatch is an open-source LLMOps platform for LLM evaluation, AI agent testing, tracing, and production observability. It combines agent … | 90 | 3511 | active |
| sugarforever/chat-ollama ChatOllama is an open-source, self-hosted AI chatbot platform built with Nuxt 3 that supports multiple LLM providers (OpenAI, Anthropic, Ge… | 63 | 3509 | active |
| NVIDIA/TransformerEngine Transformer Engine is an NVIDIA library for accelerating Transformer model training and inference on NVIDIA GPUs using low-precision format… | 99 | 3504 | active |
| borisdayma/dalle-mini DALL·E Mini is a Python library and model that generates images from a text prompt, available via pip and hosted on Hugging Face Model Hub.… | 23 | 14740 | maintenance |
| guandeh17/Self-Forcing Official implementation of Self Forcing, a training method for autoregressive video diffusion models that simulates inference during traini… | 37 | 3488 | active |
| Tencent-Hunyuan/Hunyuan3D-1 Tencent Hunyuan3D-1.0 is an open-source two-stage diffusion-based model for generating 3D assets from text prompts or images. It provides i… | 46 | 3482 | active |
| superagent-ai/grok-cli An open-source terminal-based coding agent that connects to xAI's Grok API, built with TypeScript and Bun. It offers an interactive OpenTUI… | 76 | 3434 | active |
| miaoxworld/OpenClawInstaller A shell-based one-click installer and configuration tool for deploying OpenClaw (ClawdBot), a self-hosted personal AI assistant gateway. It… | 48 | 3427 | active |
| yifanfeng97/Hyper-Extract Hyper-Extract is a Python CLI tool that transforms unstructured documents into structured knowledge using LLMs, producing graphs, hypergrap… | 76 | 3376 | active |
| agentheroes/agentheroes AgentHeroes is a self-hostable open-source application for generating AI character images, animating them into videos, and scheduling the r… | 32 | 3357 | active |
| agentscope-ai/ReMe ReMe is a Python memory management kit for AI agents that stores durable memory as ordinary Markdown files with frontmatter and wikilinks. … | 89 | 3356 | active |
| OpenTalker/SadTalker SadTalker is a CVPR 2023 deep learning tool that generates realistic talking head videos from a single portrait image and an audio clip by … | 22 | 14040 | maintenance |
| HKUDS/VideoRAG VideoRAG is a retrieval-augmented generation framework for chatting with and understanding extremely long-context videos, using a dual-chan… | 53 | 3337 | active |
| ahmetoner/whisper-asr-webservice A Dockerized REST webservice that wraps OpenAI Whisper (plus Faster Whisper and WhisperX engines) for automatic speech recognition. It expo… | 93 | 3326 | active |
| modelscope/evalscope EvalScope is a Python framework from the ModelScope community for evaluating large language models, vision-language models, embedding model… | 93 | 3312 | active |
| automazeio/vibeproxy VibeProxy is a native macOS menu bar app that proxies AI coding tools' API requests through your existing Claude Code, ChatGPT, Gemini, Kim… | 80 | 3308 | active |
| XiaoMi/xiaomi-miloco Xiaomi Miloco is an open-source whole-home intelligence solution that uses Mi Home camera video/audio as a full-modal perception gateway an… | 82 | 3292 | active |
| Ar9av/obsidian-wiki A skill-based Python framework that lets AI coding agents (Claude Code, Cursor, Codex, etc.) build and maintain an Obsidian markdown knowle… | 81 | 3289 | active |
| docker/docker-agent Docker Agent is an open-source CLI (and Docker CLI plugin) that lets developers build, run, and share AI agents defined declaratively in YA… | 80 | 3289 | active |
| rag-web-ui/rag-web-ui RAG Web UI is a self-hosted intelligent dialogue application that builds Q&A systems over your own knowledge base using Retrieval-Augmented… | 70 | 3270 | active |
| cool-admin cool-admin is an open-source admin/permission management framework built on Node.js (Midway, TypeORM, TypeScript) for the backend and Vue 3… | 74 | 3265 | active |
| butterbase-ai/butterbase Butterbase is an open-source, AI-native backend-as-a-service platform built on Postgres, providing auth, storage, serverless functions, an … | 58 | 3259 | active |
| nexu-io/nexu nexu is an open-source desktop client that runs an OpenClaw AI agent inside messaging apps like WeChat, Feishu, Slack, and Discord with one… | 66 | 3258 | active |
| AprilNEA/AChat AChat is an open-source, self-hosted, local-first AI chat platform for enterprises and teams, supporting multiple LLM providers like OpenAI… | 55 | 3255 | active |
| Tencent-Hunyuan/HunyuanImage-3.0 HunyuanImage-3.0 is Tencent's open-source native multimodal model for text-to-image and image-to-image generation, with inference code and … | 57 | 3253 | active |
| rsxdalv/TTS-WebUI TTS WebUI is a free, open-source web interface combining Gradio and React that unifies 30+ AI models for text-to-speech, voice conversion, … | 89 | 3244 | active |
| onnx/onnx-tensorrt A C++ parser library and backend that converts ONNX models into TensorRT engines for high-performance GPU inference. It is maintained by NV… | 92 | 3228 | active |
| zLanqing/codex-claude-academic-skills A collection of three academic skill packages for Claude Code and Codex covering paper writing, academic Word/PPT document generation, and … | 51 | 3220 | active |
| AutoMaker-Org/automaker Automaker is an open-source, local agentic IDE that lets users manage software tasks on a Kanban board and have autonomous AI agents (power… | 67 | 3214 | active |
| jy0205/Pyramid-Flow Pyramid Flow is the official PyTorch implementation of a training-efficient autoregressive video generation model based on pyramidal flow m… | 22 | 3208 | active |
| OpenGVLab/InternGPT InternGPT (iGPT) is an open-source demo platform for showcasing AI models through a pointing-language-driven visual interactive system, sup… | 29 | 3205 | active |
| dotnet/extensions A suite of .NET libraries from Microsoft providing production-ready capabilities such as resilience pipelines, telemetry, diagnostics, comp… | 98 | 3202 | active |
| MemMachine/MemMachine MemMachine is an open-source memory layer for AI agents and LLM applications, providing episodic, profile, and working memory that persists… | 79 | 3201 | active |
| stepfun-ai/Step-Video-T2V Step-Video-T2V is an open-source text-to-video generation model from StepFun, released with inference code and pretrained weights (includin… | 25 | 3187 | active |
| ARM-software/ComputeLibrary Arm's Compute Library is a C++ collection of over 100 low-level machine learning and computer vision functions optimized for Arm Cortex-A/N… | 96 | 3183 | active |
| smartloli/EFAK EFAK (Eagle For Apache Kafka) is an open-source, AI-enhanced monitoring and management platform for Kafka clusters, built on Spring Boot 3.… | 58 | 3179 | active |