Stars
TokenHub is a private enterprise AI gateway with role-based workspaces for users, team leaders, and administrators.
Show usage stats for OpenAI Codex and Claude Code, without having to login.
✨✨[NeurIPS 2025] This is the official implementation of our paper "Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension"
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
An automated document analyzer for Paperless-ngx using OpenAI API, Ollama, Deepseek-r1, Azure and all OpenAI API compatible Services to automatically analyze and tag your documents.
Build and run agents you can see, understand and trust.
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
🚀 The fast, Pythonic way to build MCP servers and clients.
We have made you a wrapper you can't refuse
PostgreSQL backup tool with Point-In-Time-Recovery and restore verification
All in one Qwen3-ASR Server, compatible with OpenAI API
Qwen3-ASR is an open-source series of ASR models developed by the Qwen team at Alibaba Cloud, supporting stable multilingual speech/music/song recognition, language detection and timestamp prediction.
[ICCV-2021] TransReID: Transformer-based Object Re-Identification
An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.
MinIO C++ Client SDK for Amazon S3 Compatible Cloud Storage
Bag of Tricks and A Strong Baseline for Deep Person Re-identification
使用yolov8、fast-reid、deepsort完成目标跟踪，使用yolov8、fast-reid、Faiss完成行人重识别
FlashMLA: Efficient Multi-head Latent Attention Kernels
High-performance open-source in-memory graph database for GraphRAG, AI memory, agentic AI, and real-time graph analytics. Cypher-compatible, built in C++.
Agentic AI Framework for Java Developers
A set of beautifully-designed, accessible components and a code distribution platform. Works with your favorite frameworks. Open Source. Open Code.
[ICLR 2026] Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoning
Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.
An AI model used to help with the workout session by keeping track of counts and movement.