apex-inference-chip
An inference chip design that runs a real LLM (Qwen2.5-0.5B) on FPGA — one transformer decoder layer in RTL, every silicon value bit-exact against a golden model. 0.56 tok/s measured, a 140× climb, full evidence trail.
HYSEN LABS DIRECTORY
Capability tag · curated repositories and deep analysis.
An inference chip design that runs a real LLM (Qwen2.5-0.5B) on FPGA — one transformer decoder layer in RTL, every silicon value bit-exact against a golden model. 0.56 tok/s measured, a 140× climb, full evidence trail.
A PyTorch coding practice platform — covering LLM, Diffusion, PEFT, and more A friendly environment to help you deeply understand deep learning components through hands-on practice. Like LeetCode, but for tensors. Self-hosted. Supports both Jupyter and Web interfaces.
Fuse two frontier models into one Fable-tier answer: Opus 4.8 drafts, a second model (Opus 4.8 or GPT-5.5 via codex) checks, Opus fuses. A Claude Code skill.
Host-agnostic bridge connecting Claude Code SDK to IM platforms (Telegram, Discord, Feishu)
A native connected terminal for AI agent development.
Pipeline-parallel LLM inference across GPUs on separate machines.
Claude Code skills for product market research, value props, PRDs, and go-to-market — plus the open Next Move Theory (based on AJTBD) canon and a product advisor you can /ask-nmt
Collab with OpenAI. A benchmark and harness for finding and exploiting smart contract bugs
Pentest Harness — Heaven for Hackers. A self-hosted AI agent harness for authorized pentests, bug bounty, security labs, and CTFs. Bring your own AI model API; sessions stay local.
XpertAI is an open-source platform for building, running, and evolving ai agents, providing extensible capabilities and infrastructure for diverse AI systems.
High-performance Model Context Protocol (MCP) server for Obsidian that provides AI tools with direct vault access through semantic operations and HTTP transport.
A bridge between the Xiaomi Xiao AI speaker and external AI services such as OpenClaw and XiaoZhi AI.
Tools for computational pathology
Aser is a lightweight, self-assembling AI Agent frame.
This benchmark tests how well LLMs incorporate a set of 10 mandatory story elements (characters, objects, core concepts, attributes, motivations, etc.) in a short creative story
A modular framework for benchmarking LLMs and agentic strategies on security challenges across HackTheBox, TryHackMe, PortSwigger Labs, Cybench, picoCTF and more.
🎙️ Speak with AI - Run locally using Ollama, OpenAI, Anthropic or xAI - Speech uses SparkTTS, OpenAI, ElevenLabs, Kokoro, Typecast or xAI
AutoHarness: Automated Harness Engineering for AI Agents
Privacy-first Apple Health export analyzer for CSV/JSON, charts, and local or cloud AI chat.
WeChat-to-Codex bridge for running Codex app-server from chat, with threads, slash commands, approvals, agents, automation, uploads, and assistant records.