ai-blueprint
A file-backed, spec-driven AI coding workflow framework for building real software while staying in control.
HYSEN LABS DIRECTORY
Capability tag · curated repositories and deep analysis.
A file-backed, spec-driven AI coding workflow framework for building real software while staying in control.
Named Tmux Manager: spawn, tile, and coordinate multiple AI coding agents (Claude, Codex, Gemini) across tmux panes with a TUI command palette
Run Qwen3.8-Flash-Next (125B MoE, 104 GB at 4-bit) on Macs with a fraction of that RAM by streaming experts from SSD. MLX + Swift, Ollama-compatible API.
Agent Skill for Chinese-first HyperFrames motion-video production from articles, products, websites, and README files.
Autonomous agentic AI for CRA (Cyber Resilience Act) compliance: scans repos, triages findings, opens Jira tickets, and auto-fixes vulnerabilities via PR.
Possibly the deepest AI equity-research skill: nine-chapter single-stock deep dives and earnings deep-dives, with scripted DCF/EPV/EVA and reproducible valuation. Covers US, HK and A-shares. Docs in EN and ZH.
Distill videos, PDFs, transcripts, and notes into source-backed teacher Agent Skills.
The agent responsible for conducting the agent evaluation
Spec-driven, agentic workflow framework for AI coding agents. Turn a request into a verifiable goal loop — plan, act, verify — with durable specs and evidence in your repo. Works with Claude Code, Codex, Gemini, OpenCode, and plain CLI.
Explain & debug any blackbox machine learning model with a single line of code.
Run Claude Code, Codex, and other agent CLIs in Obsidian
Educational package-manager project for AI agent skills. Not actively maintained.
Generate full-background Anthropic-style editorial illustrations with verified palette and hand-drawn visual rules.
LightningRAG is a full-stack Vue + Gin starter with a decoupled frontend and backend, plus built-in, extensible RAG (retrieval-augmented generation): knowledge bases, vector search, and integrations with many LLM and vector-store providers
AI agent tooling for data engineering workflows.
Notes for you, memory for your agents. Includes a built-in DeepSeek Harness agent; for office work, writing and coding.
ARL-Next is an automated asset reconnaissance and vulnerability monitoring platform, rebuilt from the classic ARL with upgraded Puppeteer and Nuclei engines. It closes the security loop from Tianyancha/ICP lookup to asset discovery, vulnerability scanning and threat intelligence tracking, supports minimal Docker deployment, and is friendly to AI-assisted customization.
Any research. One Claw. 🦞 From any materials to research with fully autonomous & skill-driven researcher.
An agent skills pack that turns an academic paper PDF into slides, a poster, a webpage, a Xiaohongshu post, or a WeChat article (paper2slides/poster/html/xhs/wechat)
Deterministic safety solutions for probabilistic AI agents