function: llm-inference
3362 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| zapdos-labs/unblink Unblink is an AI-powered camera monitoring application that uses a vision language model (Qwen3-VL) to analyze camera frames, summarize act… | 50 | 1507 | active |
| mbzuai-oryx/Video-ChatGPT Video-ChatGPT is a video conversation model that combines large language models with a pretrained visual encoder adapted for spatiotemporal… | 45 | 1507 | active |
| Internet-Architecture-and-Security/PacketScope PacketScope is an open-source, eBPF-based protocol stack analysis and debugging tool for server-side network observability and defense. It … | 75 | 1506 | active |
| memfreeme/memfree MemFree is an open-source hybrid AI search engine that answers questions using both your personal knowledge base and the web, integrating m… | 65 | 1506 | active |
| uccl-project/uccl UCCL is a high-performance GPU communication library written in C++ that provides collectives (as a drop-in NCCL/RCCL replacement), P2P tra… | 71 | 1504 | active |
| TencentARC/MotionCtrl MotionCtrl is the official implementation of a SIGGRAPH 2024 paper providing a unified and flexible motion controller for video generation … | 30 | 1500 | active |
| antvis/AVA AVA is an AI-native visual analytics framework from AntV that lets users load data (CSV, JSON, URL), query it in natural language, and get … | 78 | 1499 | active |
| afx-team/petercat PeterCat is an open-source system for creating intelligent Q&A chatbots for GitHub repositories, with conversational agent configuration, s… | 29 | 1495 | active |
| Soul-AILab/SoulX-FlashTalk SoulX-FlashTalk is a 14B audio-driven talking avatar model that streams infinite real-time video from a reference image and audio, achievin… | 58 | 1494 | active |
| run-llama/create-llama Create Llama is a CLI scaffolding tool that generates full-stack LlamaIndex applications with a chat interface, RAG, and agent capabilities… | 37 | 1490 | active |
| fossasia/voxbento Voxbento is an open-source, self-hosted platform for real-time simultaneous interpretation at live events. Interpreters broadcast translate… | 77 | 1483 | active |
| siddsachar/row-bot Row-Bot is a local-first desktop AI assistant and workbench that combines chat, durable memory, a personal knowledge graph, tool use, paren… | 81 | 1480 | active |
| alxndrTL/mamba.py A simple, readable pure-PyTorch (plus MLX) implementation of the Mamba state-space model architecture with a parallel scan for efficient tr… | 53 | 1478 | active |
| dirac-run/dirac Dirac is an open-source AI coding agent focused on token efficiency and context curation, claiming 50-80% API cost reduction versus other a… | 81 | 1476 | active |
| fim-ai/fim-one FIM One is a source-available, self-hostable agent platform that connects enterprise systems (global SaaS plus the China stack like Feishu,… | 59 | 1475 | active |
| bklieger-groq/stockbot-on-groq StockBot is an open-source AI chatbot that uses Llama3-70b on Groq with function calling to render live, interactive TradingView stock mark… | 40 | 1475 | active |
| kaiban-ai/KaibanJS KaibanJS is a JavaScript/TypeScript framework for building and orchestrating multi-agent AI systems using a Kanban-inspired model of Agents… | 76 | 1472 | active |
| postgresml/korvus Korvus is an open-source search SDK that unifies the entire RAG pipeline—embedding generation, vector search, reranking, summarization, and… | 25 | 1472 | active |
| Lightning-AI/lightning-thunder Lightning Thunder is a source-to-source deep learning compiler for PyTorch that optimizes models for training and inference. It provides a … | 72 | 1471 | active |
| ScottZt/jin-ce-zhi-suan A self-hosted quantitative trading research and backtesting system for Chinese A-share markets, built with Python and FastAPI with a web da… | 76 | 1468 | active |
| LingGuoAI/LingGuo-Drama LingGuo-Drama is a self-hosted, AI-powered one-stop platform for generating mini-dramas and motion comics, covering script writing, charact… | 59 | 1460 | active |
| FeiYull/TensorRT-Alpha A C++/CUDA library providing TensorRT-accelerated deployment for 30+ popular computer vision models including YOLOv3-v8, YOLOv8-Pose/Seg/Cl… | 32 | 1460 | active |
| ModelEngine-Group/app-platform AppPlatform is a self-hosted low-code platform for building, orchestrating, debugging, and deploying large language model applications such… | 76 | 1454 | active |
| zsyOAOA/InvSR InvSR is a Python research library implementing arbitrary-steps image super-resolution via diffusion inversion, leveraging pre-trained diff… | 51 | 1452 | active |
| writer/writer-framework Writer Framework is an open-source Python framework for building data and AI applications with a drag-and-drop visual editor for the fronte… | 76 | 1447 | active |
| MiroShark/MiroShark MiroShark is a universal swarm-intelligence engine that turns any document or scenario into a simulated world: it builds a Neo4j knowledge … | 59 | 1447 | active |
| hyhmrright/brooks-lint brooks-lint is an AI-powered code review plugin for Claude Code, Codex CLI, and Gemini CLI that diagnoses code against six decay risk dimen… | 81 | 1445 | active |
| evo-hq/evo Evo is a plugin for agentic coding frameworks (Claude Code, Codex, Cursor, etc.) that turns a codebase into an autoresearch loop: it discov… | 76 | 1440 | active |
| honeyandme/RAGQnASystem A medical intelligent question-answering system combining knowledge-graph RAG with large language models, built on the DiseaseKG dataset wi… | 62 | 1437 | active |
| PolyArch/humanize Humanize is a Claude Code plugin implementing RLCR (Ralph-Loop with Codex Review), an iterative development workflow where Claude implement… | 60 | 1436 | active |
| tianweiy/CausVid CausVid is a research codebase implementing a fast autoregressive video diffusion model distilled from a bidirectional diffusion transforme… | 36 | 1435 | active |
| superloglabs/superlog Superlog is an open-source agentic observability platform that ingests OpenTelemetry traces, logs, and metrics, groups noisy error signals … | 58 | 1431 | active |
| FireRedTeam/FireRedTTS2 FireRedTTS-2 is a long-form streaming text-to-speech system for multi-speaker dialogue generation, built in PyTorch with a dual-transformer… | 40 | 1431 | active |
| devnen/Chatterbox-TTS-Server A self-hosted server wrapping Resemble AI's Chatterbox TTS models behind an OpenAI-compatible API with a modern web UI. It supports voice c… | 65 | 1429 | active |
| Ch1rpy2613/Mirrai Mirrai is a self-hosted web application that builds AI 'digital twins' of people from uploaded chat logs, photos, and videos, then lets use… | 58 | 1429 | active |
| microsoft/rStar Microsoft's research repository for rStar2-Agent, a 14B math reasoning model trained with agentic reinforcement learning that autonomously … | 41 | 1427 | active |
| chunkhound/chunkhound ChunkHound is a local-first codebase intelligence CLI that indexes code with tree-sitter parsing and semantic/regex search, exposing cited … | 83 | 1426 | active |
| DEEIX-AI/DEEIX-Chat DEEIX Chat is an open-source, self-hostable enterprise AI workspace that unifies access to multiple LLM providers behind one entry point, w… | 80 | 1422 | active |
| Voine/ChatWaifu_Mobile An Android app that lets users chat with an anime-style AI companion powered by ChatGPT, with local VITS text-to-speech, Live2D character r… | 64 | 1420 | active |
| f/git-rewrite-commits A TypeScript CLI tool that uses AI (OpenAI GPT or local Ollama models) to rewrite git commit history with better, conventional commit messa… | 56 | 1420 | active |
| lenML/Speech-AI-Forge Speech-AI-Forge is a Python project built around multiple TTS generation models (ChatTTS, CosyVoice, Fish-Speech, Index-TTS, F5-TTS, FireRe… | 62 | 1418 | active |
| dexmal/dexbotic Dexbotic is an open-source PyTorch-based toolbox for developing Vision-Language-Action (VLA) models for embodied intelligence. It unifies p… | 72 | 1417 | active |
| ishaan1013/sandbox Sandbox is an open-source, cloud-based code editing environment with custom AI code autocompletion and real-time collaboration. It combines… | 25 | 1417 | active |
| zstar1003/ragflow-plus Ragflow-Plus is a fork of Ragflow, an open-source RAG (retrieval-augmented generation) platform, enhanced for practical Chinese-language us… | 64 | 1414 | active |
| OpenBMB/AgentCPM-GUI AgentCPM-GUI is an open-source 8B-parameter on-device GUI agent built on MiniCPM-V that takes Android screenshots as input and autonomously… | 46 | 1413 | active |
| gnobitab/InstaFlow InstaFlow is a one-step text-to-image generation model based on Rectified Flow, enabling ultra-fast Stable Diffusion inference without iter… | 28 | 1409 | active |
| ifindev/fullstack-next-cloudflare A production-ready full-stack template combining Next.js 15 with Cloudflare Workers, including D1 database, R2 storage, Better Auth, and Se… | 48 | 1403 | active |
| aws-samples/aws-genai-llm-chatbot A modular, production-ready AWS solution for deploying a multi-LLM, multi-RAG powered chatbot using AWS CDK. It supports Amazon Bedrock, Sa… | 60 | 1399 | active |
| remorses/kimaki Kimaki is a collaborative AI agent orchestrator that runs OpenCode coding agents from Discord, mapping projects to channels and coding sess… | 80 | 1396 | active |
| Houseofmvps/codesight codesight is a zero-dependency Node.js CLI that scans a codebase and generates a compact AI context map (routes, schemas, components, depen… | 57 | 1395 | active |
| microsoft/azurechat Azure Chat is a solution accelerator from Microsoft that lets organizations deploy a private, enterprise-grade chat application powered by … | 73 | 1392 | active |
| agent0ai/space-agent Space Agent is an AI agent application, created by the Agent Zero team, that runs in the browser/frontend runtime and can build pages, tool… | 69 | 1392 | active |
| SebastienZh/StockTradebyZ A semi-automated stock screening application for China's A-share market that fetches daily K-line data via Tushare, applies quantitative pr… | 51 | 1392 | active |
| arkohut/pensieve Pensieve is a privacy-focused passive screen recording application that automatically takes screenshots of your screens, indexes them with … | 85 | 1386 | active |
| larlarua/AutoCVE AutoCVE is a self-hosted multi-agent platform that automates CVE discovery: it filters target projects, imports repositories, audits source… | 77 | 1386 | active |
| xaitax/SploitScan SploitScan is a Python CLI cybersecurity utility that aggregates detailed vulnerability information for CVEs from sources like EPSS, CISA K… | 77 | 1384 | active |
| nlkitai/nlux NLUX is an open-source React and JavaScript library for building conversational AI chat interfaces powered by large language models. It pro… | 51 | 1380 | active |
| nyrahealth/CrisperWhisper CrisperWhisper 2.0 is a controllable speech recognition model and Python library that transcribes audio either verbatim (including fillers,… | 89 | 1375 | active |
| AgibotTech/genie_sim Genie Sim is AgiBot's open-source simulation platform for embodied intelligence, providing environment reconstruction, LLM-driven scene gen… | 74 | 1374 | active |
| lvwzhen/law-cn-ai An AI legal assistant for Chinese law that answers questions using a knowledge base of Chinese legal documents. It is a Next.js app that em… | 30 | 4909 | maintenance |
| moyangzhan/langchain4j-aideepin LangChain4j-AIDeepin is an open-source, self-hostable AI application platform built on Spring Boot, LangChain4j, and LangGraph4j with Vue 3… | 91 | 1368 | active |
| PurpleDoubleD/locally-uncensored Locally Uncensored is a free, open-source desktop AI studio (built with Tauri/TypeScript) that bundles uncensored local chat, a coding agen… | 81 | 1366 | active |
| andyhuo520/aetherviz-master AetherViz Master is an AI-powered interactive educational visualization tool that turns any teaching topic into an immersive 3D interactive… | 50 | 1365 | active |
| 79E/ChatGpt-Web A commercially-viable ChatGPT web application built with React and TypeScript, featuring a full admin backend for managing users, tokens, p… | 26 | 1363 | active |
| xlang-ai/OpenAgents OpenAgents is an open platform for using and hosting LLM-powered language agents, featuring a Data Agent for Python/SQL analysis, a Plugins… | 28 | 4859 | maintenance |
| Amm1rr/WebAI-to-API A self-hosted Python server that exposes browser-based AI services like Google Gemini through an OpenAI-compatible /v1/chat/completions API… | 91 | 1356 | active |
| lxtGH/OMG-Seg Official research codebase for OMG-Seg (CVPR 2024) and OMG-LLaVA (NeurIPS 2024), unified models for image-level, object-level, and pixel-le… | 47 | 1354 | active |
| morettt/my-neuro An open-source AI desktop companion framework inspired by Neuro-sama, letting users build a customizable Live2D character with sub-second v… | 84 | 1353 | active |
| muzishen/IMAGDressing IMAGDressing-v1 is a diffusion-based framework for customizable virtual dressing that generates human images with fixed garments and contro… | 44 | 1343 | active |
| unslop-xyz/noodles Noodles is a Python CLI tool that builds function call graphs from codebases using tree-sitter AST parsing and renders them as interactive … | 48 | 1342 | active |
| joey-zhou/xiaozhi-esp32-server-java A Java enterprise-grade server and management platform for the Xiaozhi ESP32 AI voice assistant hardware, providing a full front-end/back-e… | 69 | 1337 | active |
| bytedance/Lance Lance is a 3B-parameter native unified multimodal model from ByteDance for image and video understanding, generation, and editing, trained … | 55 | 1335 | active |
| stulzq/azure-openai-proxy A Go-based proxy service that converts OpenAI official API requests into Azure OpenAI API requests, letting OpenAI-ecosystem tools use Azur… | 21 | 1335 | stable |
| coulsontl/ai-toolbox A cross-platform desktop application (built with Tauri and Rust) for managing configurations of AI coding assistant CLIs such as Claude Cod… | 79 | 1333 | active |
| supermemoryai/opensearch-ai OpenSearch GPT is a personalised AI search engine web application that learns about users and their interests as they browse the web. It is… | 37 | 1329 | active |
| gavrielc/Nano-PDF A Python CLI tool that edits PDF slides using natural language prompts, powered by Google's Gemini 3 Pro Image model. It renders pages to i… | 41 | 1326 | active |
| shuyu-labs/AntSK AntSK is an enterprise AI knowledge base and agent platform built on .NET 9, Blazor, Semantic Kernel, and Kernel Memory. It supports import… | 53 | 1325 | active |
| aws-samples/bedrock-chat Bedrock Chat (BrChat) is a multilingual generative AI chat platform built on Amazon Bedrock, deployable via AWS CDK. It supports chat, cust… | 90 | 1322 | active |
| CBIhalsen/PolyglotPDF PolyglotPDF is a Python-based multilingual eBook and PDF translation tool that preserves original layouts while translating, supporting bot… | 42 | 1320 | active |
| darwin-lau/langmanus LangManus is a community-driven Python framework for building hierarchical multi-agent AI automation systems, where a supervisor coordinate… | 25 | 1316 | active |
| cased/kit kit is a Python toolkit for code intelligence and context engineering, providing codebase mapping, tree-sitter-based symbol extraction, gre… | 57 | 1314 | active |
| inference-labs-inc/JSTprove JSTprove is a Rust CLI toolkit that generates zero-knowledge proofs of machine learning inference on ONNX models, built on Polyhedra Networ… | 70 | 1312 | active |
| apecloud/ApeRAG ApeRAG is a production-ready RAG platform combining Graph RAG, vector search, and full-text search with AI agents and MCP support. It offer… | 55 | 1308 | active |
| StarlightSearch/EmbedAnything EmbedAnything is a high-performance, memory-safe embedding pipeline written in Rust (with Python bindings) that generates embeddings from t… | 88 | 1306 | active |
| bytedance/Bernini Bernini is a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer perf… | 57 | 1305 | active |
| HG-ha/MTools MTools is a cross-platform desktop application built with Python and Flet that bundles image processing, audio/video editing, text operatio… | 83 | 1304 | active |
| kantord/SeaGOAT SeaGOAT is a local-first semantic code search engine that uses vector embeddings to let developers search their codebase with natural langu… | 72 | 1303 | active |
| Henry-23/VideoChat A real-time voice-interactive digital human application that combines ASR, LLM, TTS, and talking-head generation (MuseTalk) into a low-late… | 48 | 1303 | active |
| Albert-Weasker/niubi_guard An open-source defense system that protects GitHub repositories from spam, harassment, and coordinated abuse via configurable detection sig… | 65 | 1301 | active |
| utkusen/sast-skills A collection of LLM agent skills that turn coding assistants like Claude Code, Codex, Opencode, and Cursor into a SAST (static application … | 49 | 1297 | active |
| wisupai/e2m E2M is a Python library that parses and converts many file types (doc, docx, epub, html, url, pdf, ppt, pptx, mp3, m4a) into Markdown using… | 23 | 1295 | active |
| codefuse-ai/codefuse-chatbot CodeFuse-ChatBot is an open-source AI assistant for the software development lifecycle, combining a multi-agent scheduling framework with D… | 27 | 1291 | active |
| huanngzh/MV-Adapter MV-Adapter is a plug-and-play adapter that turns pre-trained text-to-image diffusion models (e.g., SDXL, SD2.1) into multi-view consistent … | 34 | 1290 | active |
| SmythOS/sre SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime, SDK, and CLI for building and running production AI agents acros… | 52 | 1289 | active |
| Phantom-video/HuMo HuMo is a research model and Python codebase from Tsinghua University and ByteDance for human-centric video generation using collaborative … | 46 | 1285 | active |
| higress-group/himarket HiMarket is an enterprise-grade AI open platform built on the Higress AI Gateway that lets organizations run a private AI capability market… | 84 | 1284 | active |
| fatwang2/search2ai A proxy service that adds online search, news, and webpage summarization capabilities to any OpenAI-compatible LLM API via function calling… | 79 | 1280 | active |
| LangChat/langchat LangChat is a Java-based enterprise AIGC platform for building AI knowledge bases, chatbots, and agent applications with multi-provider LLM… | 46 | 1279 | active |
| gomate-community/TrustRAG TrustRAG is a configurable and modular Retrieval-Augmented Generation (RAG) framework in Python built around the principle of reliable inpu… | 53 | 1277 | active |
| LiteLLM-Labs/litellm-agent-control-plane LiteLLM Agent Control Plane is a self-hosted platform that provides one unified API and UI for creating and running AI agents across multip… | 53 | 1267 | active |