Python

A Python framework that emulates Grok Heavy functionality using intelligent multi-agent orchestration. Deploy 4 (or more) specialized AI agents in parallel to deliver comprehensive, multi-perspective analysis on any query.

AI Vtuber for Streaming on Youtube/Twitch

Example of Microservices written using Flask.

Open-source deep-learning framework for exploring, building and deploying AI weather/climate workflows.

[ICLR 2026] Agentic Reinforced Policy Optimization (ARPO)

使用有道翻译你想知道的单词和语句

We introduce the Audio Logical Reasoning (ALR) dataset, consisting of 6,446 text-audio annotated samples specifically designed for complex reasoning tasks. Building on this resource, we propose SoundMind, a rule-based reinforcement learning (RL) algorithm tailored to endow audio language models (ALMs) with deep bimodal reasoning abilities.

VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold

RAGChecker: A Fine-grained Framework For Diagnosing RAG

Real-time audio visualizations (spectrum, spectrogram, etc.)

Automatically archive links to videos, images, and social media content from Google Sheets (and more).

An AI-powered threat modeling tool that leverages OpenAI's GPT models to generate threat models for a given application based on the STRIDE methodology.

Disables the "No valid subscription" dialog on all Proxmox products, all versions.

Backup and restore your Django database and media

AxisAgentic: An Extensible Runtime and Trajectory-Collection Framework for Long-Horizon Agents.

Creator Buddy: orchestrated Agent Skills for cross-platform content search, creator analysis, and viral trend research

Build AI applications that can see, hear, and speak using your screens, microphones, and cameras as inputs.

✨ Hotshot-XL: State-of-the-art AI text-to-GIF model trained to work alongside Stable Diffusion XL

Based on GroundingDino and SAM, use semantic strings to segment any element in an image. The comfyui version of sd-webui-segment-anything.

Evaluate your LLM's response with Prometheus and GPT4 💯

🚀 2024-至今 1Day 漏洞 PoC 深度研究与复现归档。涵盖 OA、ERP、安防、数通、大模型及容器等 高价值资产漏洞，实战导向，助力安全研究与合规检测。

WeMM-Embedding is a family of universal multimodal embedding models by the WeChat Vision Team at Tencent, supporting multimodal understanding and retrieval.

Stack overflow command line client. Search and browse stack overflow without leaving the terminal :computer:

MCP server to access Garmin data

Asynchronous Advantage Actor-Critic (A3C) algorithm for Super Mario Bros

Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA

An open-source OpusClip alternative

Seasons, absolute mode, Subfolders...

A lightweight and robust Python eye tracker

Kolibri Learning Platform: the offline app for universal education