HYSEN LABS DIRECTORY
License tag · curated repositories and deep analysis.
The best DeepSeek Harness plugin for context insight and management, with a context dashboard, browser, sidebar and context command, for context statistics, composition, breakdown and evolution details - understanding how the context is made and how it evolves.
Unified real-time search MCP server supporting general web search, vertical domain search, parallel batch search, and full-page URL content extraction.
An LLM-based (DeepSeek, OpenAI, etc.) automated code review tool for GitLab; supports pushing notifications and generating daily reports via DingTalk/WeCom/Lark, Docker deployment, and a visual dashboard.
A general-purpose probabilistic programming system with programmable inference
A Go framework for building production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, evaluation, and observability.
A local desktop app that turns videos and images into 3D Gaussian Splats in one click.
Project brief: Shorten URLs using invisible spaces. Individuals Organizations [Support this project with your organization][open-collective].
Buildroot-based, cloud-free smart-home platform for a Homematic IP CCU (CCU3/ELV-Charly). Runs on Raspberry Pi & x86/ARM or as a virtual appliance (Proxmox VE, Home Assistant, Docker/LXC/K8s)...
SkillsBench evaluates how well skills work and how effective agents are at using them.
A collection of original, innovative ideas and algorithms towards Advanced Literate Machinery. This project is maintained by the OCR Team in the Language Technology Lab, Tongyi Lab, Alibaba Group.
Communication infrastructure for the AI era, one binary, one broker, one storage layer, any protocol.
Generate automated tests for your Node.js app via LLMs without developers having to write a single line of code.
Rust library for quantitative finance.
Control panel for VLLM, Sglang, llama.cpp, exllamav3
Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ.
The open source Solver AI for Java and Kotlin to optimize scheduling and routing. Solve the vehicle routing problem, employee rostering, task assignment, maintenance scheduling and other planning problems.
Cloud native, ultra-high-performance AI & API gateway: LLM API management, distribution system and open platform supporting all AI APIs, including OpenAI, Azure, Anthropic Claude, Google Gemini, DeepSeek, ByteDance Doubao, ChatGLM, Wenxin Yiyan, Xunfei Spark, Tongyi Qianwen, 360 Zhinao, Tencent Hunyuan and more. Unifies API requests and responses, application approval, call statistics, load balancing and multi-model failover. One-click deployment, ready to use out of the box.
Mellea is a library for writing generative programs.
Magenta RealTime 2: An Open-Weights Live Music Model
Open Source Continuous Inference Benchmark Research Platform, Kimi K2.7-Code, MiniMax M3, DeepSeekv4, GLM5 - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72 & soon TPUv6e/v7/Trainium2/3 | , Kimi K2.7-Code MiniMax M3 DeepSeekv4 GLM5 - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72 TPUv6e/v7/Trainium2/3.