Lance
A 3B-active-parameter native unified multimodal model for image and video understanding, generation, and editing.
HYSEN LABS DIRECTORY
Language tag · curated repositories and deep analysis.
A 3B-active-parameter native unified multimodal model for image and video understanding, generation, and editing.
Xiaohongshu (RED) creator MCP toolkit, supporting content creation and publishing tools that integrate with AI clients.
TripoSplat converts a single 2D image into high-quality and variable number of 3D Gaussians, developed by TripoAI.
Building LLM-Enabled Multi Agent Applications from Scratch
Turn any AI agent into a computational researcher. HexStellar Cortex delivers software-accelerated optimization, quantum computing, scientific computing, decision intelligence, and verifiable execution through a Python CLI and API—with certainty labels, verification receipts, examples, and a free sandbox. Start instantly: pip install hexstellar
extract all your personal data history from cursor, codex, claude-code, windsurf, and trae
All-in-One Multimodal Parsing Engine + Ontology-Powered, LLM Wiki-Driven AI-Ready Knowledge Engine
Build, train, optimize, and run computer vision models locally, from raw images to live inference. Open source, optimized for Intel XPU (CPU-only and CUDA also supported).
LiveBench: A Challenging, Contamination-Free LLM Benchmark
CleverCSV is a Python package for handling messy CSV files. It provides a drop-in replacement for the builtin CSV module with improved dialect detection, and comes with a handy command line application for working with CSV files.
🦞+🔬 NanoResearch: The Autonomous AI Research Assistant
agent skills for vibe motion
Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.
Effortlessly request recommended movies, TV shows and anime to Jellyseer/Overseer based on your recently watched content on Jellyfin, Plex or Emby—let SuggestArr handle it all automatically, keeping your library fresh with new and exciting content!
High performance, easy-to-use, and scalable package for learning large-scale knowledge graph embeddings.
SGLang-Omni is a high-performance serving framework for audio models (TTS, ASR) and unified multimodal models.
AI-powered tool for efficient abstract and PDF screening in systematic reviews.
A self-organizing multi-agent collaboration platform for OpenClaw. Multiple AI agents work as an autonomous team — planning, executing, reviewing, and patrolling tasks with zero human intervention.
Bernini is a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer.
Daily updated LLM papers.