TurboVLA
TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM
HYSEN LABS DIRECTORY
License tag · curated repositories and deep analysis.
TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM
A go implementation of the STUN client (RFC 3489 and RFC 5389)
An active monitoring software to detect failures before your customers do.
Towards a Generative 3D World Engine for Embodied Intelligence
OpenStack Identity (Keystone). Mirror of code maintained at opendev.org.
Vulkan, OptiX and CUDA Interoperation Modular Rendering Library and Framework for PC/Linux/Android
Async-friendly WebTransport implementation in Rust
LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.
Google Cloud Platform Vertex AI end-to-end workflows for machine learning operations
A push parser for the HTTP 1.x protocol in Rust.
Serverless LLM Serving for Everyone.
A free and open vulnerabilities database and the packages they impact. And the tools to aggregate and correlate these vulnerabilities. Sponsored by NLnet https://nlnet.nl/project/vulnerabilitydatabase/ for https://www.aboutcode.org/ Chat at https://gitter.im/aboutcode-org/vulnerablecode Docs at https://vulnerablecode.readthedocs.org/
Orchestra is a human-in-the-loop AI system for orchestrating project teams of experts and machines.
Tencent Cloud API 3.0 SDK for Python
Java embedded PostgreSQL component for testing
Official Implementation for EMNLP 2024 (Main Track, Oral) "AgentReview: Exploring Academic Peer Review with LLM Agent."
On-device Speech-to-Intent engine powered by deep learning
Fast C++ and Python library for state-vector simulation of quantum circuits.
Perpetual is a high-performance gradient boosting machine. It delivers optimal accuracy in a single run without complex tuning through a simple budget parameter. It features out-of-the-box support for causal ML, continual learning, native calibration, and robust drift monitoring, along with Rust core and zero-copy bindings for Python and R
A geo-distributed KV store for metadata management