function: llm-inference
3362 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| memoavatar/memo MEMO is an open-weight diffusion model for generating expressive, identity-consistent talking videos from a single reference image and an a… | 40 | 1072 | active |
| GanymedeNil/document.ai A universal local knowledge base solution that stores documents as vectors in a vector database and uses GPT3.5 to generate answers from re… | 30 | 3669 | maintenance |
| trendy-design/llmchat LLMChat is a privacy-focused AI chat platform built with Next.js and TypeScript that provides a unified interface for chatting with multipl… | 24 | 1071 | active |
| THUDM/GLM GLM is a general language model pretrained with an autoregressive blank-filling objective, released with pretrained checkpoints and fine-tu… | 32 | 3666 | maintenance |
| christian-fei/my-yt A self-hosted, minimal YouTube frontend built with vanilla JavaScript and yt-dlp that lets you manage channel subscriptions, download video… | 64 | 1070 | active |
| gangweix/pixel-perfect-depth Pixel-Perfect Depth is a monocular depth estimation model based on pixel-space diffusion transformers that produces flying-pixel-free depth… | 49 | 1066 | active |
| Lazarus-AI/clearwing Clearwing is a dual-mode autonomous offensive-security tool that combines a network-pentest ReAct agent with an LLM-driven source-code vuln… | 63 | 1063 | active |
| abertsch72/unlimiformer Unlimiformer is a method and official implementation for augmenting pretrained encoder-decoder transformers with retrieval-based attention,… | 30 | 1062 | stable |
| vijishmadhavan/ArtLine ArtLine is a deep learning project that converts portrait photos into line art portraits, with a ControlNet-based variant that adjusts styl… | 32 | 3631 | maintenance |
| getrebuild/rebuild REBUILD is a highly configurable, open-source (GPL-3.0) enterprise management system built in Java/Spring Boot that lets organizations buil… | 100 | 1061 | active |
| JudgmentLabs/judgeval Judgeval is an open-source Python SDK for LLM agent improvement, providing OpenTelemetry-based tracing and prompt-based agent-judge evaluat… | 84 | 1060 | active |
| rogue-security/rogue Rogue is an open-source AI agent evaluator and red teaming platform that stress-tests agents against business policies and simulated advers… | 78 | 1060 | active |
| yokingma/SearChat SearChat is a self-hostable AI-powered conversational search engine that combines web search (Bing, Google, SearXNG) with multi-turn chat b… | 87 | 1059 | active |
| tegnike/aituber-kit AITuberKit is an all-in-one web application toolkit for building and deploying AI character chat experiences, including streaming-oriented … | 89 | 1056 | active |
| Tencent-Hunyuan/HunyuanVideo-Foley HunyuanVideo-Foley is a multimodal diffusion model from Tencent Hunyuan that generates high-fidelity Foley sound effects synchronized with … | 37 | 1055 | active |
| lennybase/browsernode Browsernode is a TypeScript implementation of Browser-use that lets LLM-powered AI agents control a web browser via Playwright. It provides… | 34 | 1055 | active |
| Artrajz/vits-simple-api A Python HTTP API service that exposes VITS-family text-to-speech models (VITS, Bert-VITS2, GPT-SoVITS, W2V2 emotional VITS) for inference.… | 69 | 1051 | active |
| shang-zhu/violin Violin is an open-source video translation tool that transcribes speech, translates it into 33 languages, synthesizes a native-sounding voi… | 52 | 1051 | active |
| aiptimizer/TurboOCR TurboOCR is an extremely fast GPU-accelerated document parser written in C++ that combines OCR, layout analysis, table extraction, and form… | 82 | 1049 | active |
| zai-org/SCAIL SCAIL is the official inference implementation of a 14B diffusion transformer model that generates studio-grade character animation videos … | 52 | 1048 | active |
| agents-flex/agents-flex Agents-Flex is a lightweight, modular Java framework for building AI applications and agents, positioned as a Java counterpart to Spring AI… | 93 | 1046 | active |
| kreneskyp/ix IX is a self-hosted platform for designing, running, and scaling autonomous and semi-autonomous LLM-powered agents and workflows. It includ… | 48 | 1046 | active |
| LocoreMind/locoagent LocoAgent is an AI-powered social media agent that autonomously operates real accounts through genuine browser automation via Chrome DevToo… | 72 | 1045 | active |
| PandaAI QuantFlow PandaFactor is a Python quantitative factor library for financial data analysis, technical indicator computation, and alpha factor construc… | 25 | 1041 | active |
| D2I-CUHKSZ/MicroWorld MicroWorld is a lightweight Python engine that turns multi-modal event materials (documents, images, videos, graph signals) into structured… | 53 | 1039 | active |
| kijai/ComfyUI-Hunyuan3DWrapper A ComfyUI custom node wrapper for Tencent's Hunyuan3D-2 model, enabling 3D asset generation from images or text directly inside ComfyUI wor… | 53 | 1039 | active |
| iptag/jimeng-api A self-hosted API service that reverse-engineers Jimeng AI (China) and Dreamina (international) to expose free AI image and video generatio… | 10 | 1038 | active |
| mohammed-bahumaish/prisma-editor A web application for visualizing and editing Prisma schemas with real-time ER diagrams and direct graph-based editing. It also supports sh… | 68 | 1037 | active |
| Soul-AILab/SoulX-FlashHead SoulX-FlashHead is a 1.3B-parameter framework for high-fidelity, infinite-length, real-time streaming talking-head portrait video generatio… | 53 | 1037 | active |
| webwhiz-ai/webwhiz WebWhiz is an open-source, self-hostable application that trains a ChatGPT-powered chatbot on your website data by crawling your pages and … | 48 | 1037 | active |
| susiai/susi_chat A chat interface for communicating with a locally hosted LLM (via llama.cpp) through a terminal console, a browser-based console, or a voic… | 61 | 1036 | active |
| OpenBMB/RepoAgent RepoAgent is an LLM-powered framework that automatically generates repository-level code documentation by detecting changes in Git reposito… | 24 | 1036 | active |
| inclusionAI/UI-Venus UI-Venus is a family of open-source multimodal GUI agent models (9B/27B) that perform UI element grounding and task navigation from screens… | 63 | 1034 | active |
| forcedotcom/salesforcedx-vscode The official Salesforce Extensions for Visual Studio Code, providing Salesforce DX development tooling including Apex language support, deb… | 96 | 1033 | active |
| Agentic Document Extraction (ADE) The official CLI for LandingAI's Agentic Document Extraction (ADE), which parses documents into grounded Markdown and elements and extracts… | 84 | 1032 | active |
| Kappaemme-git/codex-first-customer-finder-skill A Codex skill (plugin) that takes a startup URL or product idea and produces an evidence-backed shortlist of potential first customers from… | 57 | 1027 | active |
| vastxie/99AI 99AI is a commercially viable, self-hostable AI web platform built with Vue and Node.js that bundles AI chat, image/video/music generation,… | 35 | 1027 | active |
| beizhu-1209/AIHelms AIHelms is a self-hosted enterprise AI resource governance platform that provides a unified AI gateway for managing models from OpenAI, Azu… | 81 | 1025 | active |
| zai-org/GLM-Image GLM-Image is an open-source image generation model combining a 9B autoregressive generator with a 7B diffusion decoder, excelling at text r… | 48 | 1025 | active |
| harehare/mq mq is a jq-like command-line tool and query language for slicing, filtering, and transforming Markdown via its AST, written in Rust as a si… | 83 | 1024 | active |
| MGdaasLab/WHartTest WHartTest is an AI-driven test automation platform built on Django 5.2 + DRF with a Vue frontend, generating and managing executable test c… | 83 | 1024 | active |
| Alpha-VLLM/Lumina-DiMOO Lumina-DiMOO is an open-source omni diffusion large language model that uses fully discrete diffusion to handle multimodal inputs and outpu… | 55 | 1020 | active |
| bxx2004/FUNGA FUNGA (Functional Gene Annotation Exploitation Platform) is an AI-powered web platform for mining gene functions, integrating cross-species… | 38 | 1020 | active |
| amchii/tg-signer A Python CLI tool (with optional WebUI and Docker images) that automates Telegram tasks using a user account session, such as daily check-i… | 91 | 1019 | active |
| towhee-io/towhee Towhee is a Python framework for building ETL pipelines that process unstructured data (images, video, text, audio) into embeddings using s… | 23 | 3453 | maintenance |
| marcus/nightshift Nightshift is a Go CLI tool that runs overnight, using your leftover Claude or Codex token budget to automatically find issues like dead co… | 71 | 1011 | active |
| octimot/StoryToolkitAI StoryToolkitAI is a desktop film editing tool that transcribes, indexes, and semantically searches video footage locally, using speech reco… | 65 | 1009 | active |
| MeiGen-AI/PosterCraft PosterCraft is a unified framework for generating high-quality aesthetic posters, published as an ICLR 2026 paper. It provides model weight… | 48 | 1009 | active |
| themanojdesai/python-a2a Python A2A is a Python library implementing Google's Agent-to-Agent (A2A) protocol with Model Context Protocol (MCP) integration. It enable… | 37 | 1008 | active |
| gausian-AI/Gausian_native_editor Gausian is a native desktop video editor built in Rust with GPU-accelerated preview (WGPU), timeline editing, and hardware decoding via Vid… | 53 | 1006 | active |
| mit-han-lab/efficientvit A collection of efficient vision foundation models from MIT Han Lab, including EfficientViT backbones for perception, EfficientViT-SAM for … | 48 | 3358 | maintenance |
| guangzhengli/ChatFiles ChatFiles is a Next.js web application that lets users upload documents and chat with them using GPT and embeddings via LangChainJS and a S… | 21 | 3340 | maintenance |
| ourongxing/chatgpt-vercel A self-hostable ChatGPT web client built with SolidStart and deployed on Vercel edge functions, powered by the OpenAI API. It offers an ele… | 10 | 3208 | maintenance |
| andrewyng/openworker OpenWorker is an open-source desktop AI agent application that completes real work end-to-end — code security reviews with fix branches, cl… | 80 | 17302 | experimental |
| linsa-io/linsa.io Linsa is a privacy-focused messaging application that combines chat, tasks, notes, files, and payments into a single product with end-to-en… | 76 | 16860 | experimental |
| ElricLiu/AutoGPT-Next-Web A web UI for assembling, configuring, and deploying autonomous AI agents (AutoGPT/AgentGPT-style) directly in the browser, built with Next.… | 23 | 3000 | maintenance |
| weaigc/bingo Bingo is a self-hostable web application that recreates the New Bing (Bing AI / Copilot) chat interface, allowing access to Bing AI feature… | 28 | 2828 | maintenance |
| kyegomez/OpenMythos OpenMythos is an open-source, theoretical PyTorch implementation of a Recurrent-Depth Transformer (RDT) architecture inspired by speculatio… | 51 | 14872 | experimental |
| mckaywrigley/paul-graham-gpt An open-source AI-powered search and chat application built over Paul Graham's essays using OpenAI embeddings, pgvector on Supabase, and GP… | 30 | 2663 | maintenance |
| waooAI/waoowaoo waoowaoo is a self-hosted AI film and video production studio that turns novel or script text into complete videos, automatically generatin… | 74 | 13956 | experimental |
| SUSI.AI SUSI.AI is an open-source personal assistant platform whose Java server holds the assistant's 'intelligence', answering chat and voice quer… | 10 | 2521 | maintenance |
| CjangCjengh/MoeGoe MoeGoe is an executable command-line tool for running inference with VITS text-to-speech models, supporting TTS, voice conversion, HuBERT-V… | 23 | 2421 | maintenance |
| cogentapps/chat-with-gpt An open-source, self-hostable ChatGPT web app built with TypeScript and React that adds voice features via ElevenLabs text-to-speech and Op… | 30 | 2350 | maintenance |
| langchain-ai/langserve LangServe is a Python library that deploys LangChain runnables and chains as REST APIs built on FastAPI, with automatic input/output schema… | 10 | 2328 | maintenance |
| MetaGLM/FinGLM FinGLM is an open, community-driven financial LLM project centered on a dialog-based question-answering system that analyzes Chinese listed… | 27 | 2261 | maintenance |
| Tracer-Cloud/opensre OpenSRE is an open-source Python framework for building AI SRE agents that investigate incidents and perform root cause analysis on your in… | 78 | 10999 | experimental |
| dog-qiuqiu/Yolo-Fastest Yolo-Fastest is an ultra-lightweight YOLO-based object detection algorithm and model zoo, with only ~250 MFLOPs and a 666KB ncnn model. It … | 23 | 2103 | maintenance |
| NVlabs/alpamayo NVIDIA Alpamayo 1 is an open 10B-parameter reasoning vision-language-action (VLA) model for autonomous vehicles that pairs driving trajecto… | 59 | 2014 | maintenance |
| joschan21/quill Quill is a fullstack SaaS application built with Next.js 13 App Router, tRPC, Prisma, and Tailwind that lets users upload PDFs and chat wit… | 27 | 2004 | maintenance |
| aws/amazon-q-developer-cli Amazon Q Developer CLI is an open-source Rust-based terminal tool providing an agentic AI chat experience for building applications with na… | 74 | 1985 | maintenance |
| Anse Anse is a minimal, self-hostable web UI for chatting with OpenAI's ChatGPT models (GPT-3.5 Turbo and GPT-4) via the OpenAI API. Built with … | 30 | 1969 | maintenance |
| FoundationVision/LlamaGen LlamaGen is a family of autoregressive image generation models that apply next-token prediction, as in Llama-style LLMs, to visual generati… | 24 | 1966 | maintenance |
| alejandro-ao/ask-multiple-pdfs A Streamlit-based Python application built with Langchain that lets users chat with multiple PDF documents using natural language. It extra… | 29 | 1874 | maintenance |
| nlpodyssey/spago Spago is a self-contained machine learning and NLP library written in pure Go, featuring an asynchronous computation graph with automatic d… | 29 | 1850 | maintenance |
| ermongroup/ddim Official PyTorch implementation of Denoising Diffusion Implicit Models (DDIM), a faster sampling method for diffusion probabilistic models.… | 32 | 1846 | maintenance |
| sammcj/gollama Gollama is a Go-based TUI tool for managing Ollama models on macOS and Linux. It lets users list, inspect, sort, edit, run, unload, copy, r… | 80 | 1837 | maintenance |
| impira/docquery DocQuery is a Python library and CLI tool that uses large language models to answer questions about semi-structured and unstructured docume… | 32 | 1775 | maintenance |
| reworkd/tarsier Tarsier is a Python library providing vision utilities for LLM-driven web interaction agents. It visually tags interactable page elements w… | 17 | 1761 | maintenance |
| Delta-ML/delta DELTA is a deep learning based end-to-end natural language and speech processing platform built on TensorFlow and Python 3. It provides one… | 10 | 1607 | maintenance |
| yakGPT/yakGPT YakGPT is a locally running, browser-based ChatGPT UI that connects directly to the OpenAI API with your own key. It adds hands-free voice … | 30 | 1586 | maintenance |
| thu-ml/unidiffuser UniDiffuser is a unified diffusion framework that fits marginal, conditional, and joint distributions across image and text modalities in a… | 30 | 1487 | maintenance |
| Nanjiren01/AIChatWeb AIChatWeb is a fork of ChatGPT-Next-Web that adds user registration/login, quota management, invitations, sensitive-word filtering, payment… | 29 | 1473 | maintenance |
| ebhy/budgetml BudgetML is a Python library that deploys machine learning models as secured HTTPS API endpoints on cheap GCP preemptible instances in unde… | 23 | 1343 | maintenance |
| obot-platform/nanobot Nanobot is a standalone, open-source MCP host written in Go that combines MCP servers with an LLM to build agent experiences, configurable … | 81 | 1336 | maintenance |
| kabachuha/sd-webui-text2video An Automatic1111 WebUI extension that adds text-to-video generation using diffusion models like ModelScope and VideoCrafter, relying only o… | 30 | 1322 | maintenance |
| vercel/modelfusion ModelFusion is a TypeScript library that provides a unified, vendor-neutral abstraction layer for integrating AI models into JavaScript and… | 10 | 1319 | maintenance |
| jtsang4/claude-to-chatgpt A proxy service that translates Anthropic Claude API calls into the OpenAI Chat Completions API format, so Claude can be used anywhere the … | 20 | 1297 | maintenance |
| YavorGIvanov/sam.cpp A pure C/C++ implementation of Meta's Segment Anything Model (SAM) for image segmentation inference, built on the ggml tensor library. It c… | 28 | 1276 | maintenance |
| ahrm/UnstableFusion UnstableFusion is a PyQt5 desktop frontend for Stable Diffusion that supports text-to-image generation, inpainting, img2img, and outpaintin… | 23 | 1271 | maintenance |
| SUC-DriverOld/MSST-WebUI A WebUI application for running inference with Music-Source-Separation-Training (MSST) and UVR/VR models, with preset processing flows, mod… | 69 | 1242 | maintenance |
| PlayVoice/vits_chinese A Chinese text-to-speech library combining VITS with BERT-based prosody embeddings and NaturalSpeech infer-loss features, supporting ONNX c… | 23 | 1226 | maintenance |
| 1943time/inkdown Inkdown is a WYSIWYG Markdown editor fully compatible with the GitHub Flavored Markdown spec, available as a desktop app (Electron) and a V… | 57 | 1183 | maintenance |
| all-in-aigc/sorafm Sora.FM is a self-hostable Next.js web application that showcases AI-generated videos from OpenAI's Sora text-to-video model and provides a… | 25 | 1153 | maintenance |
| showlab/Show-1 Show-1 is a research codebase implementing a text-to-video generation model that combines pixel and latent diffusion models, published at I… | 46 | 1148 | maintenance |
| CASIA-LMC-Lab/AnomalyGPT AnomalyGPT is the first Large Vision-Language Model based method for industrial anomaly detection, identifying the presence and location of… | 28 | 1133 | maintenance |
| Syan-Lin/CyberWaifu CyberWaifu is a Python chatbot application that combines LLMs (ChatGPT, Claude) with TTS (edge-tts, Azure) to create realistic conversation… | 30 | 1100 | maintenance |
| thunderbird/thunderbolt Thunderbolt is an open-source, cross-platform AI client from Thunderbird that lets users connect any OpenAI-compatible model or ACP-compati… | 80 | 4760 | experimental |
| Xchat1/cursor2api-go A Go service that converts Cursor's web interface into an OpenAI chat/completions-compatible API, exposing models like gemini-3-flash with … | 51 | 1063 | maintenance |
| bravekingzhang/text2video A Python web application that converts text (e.g., novel passages) into narrated videos. It splits text into sentences, generates images vi… | 29 | 1049 | maintenance |
| IBM/MAX-Image-Resolution-Enhancer An IBM Model Asset Exchange project that deploys an SRGAN-based image super-resolution model as a web service in a Docker container. It ups… | 42 | 1041 | maintenance |