agent-memory-vault
Markdown-first shared memory vault for Claude Code and Codex with SQLite, Zvec, Git, closeout, and audit
HYSEN LABS DIRECTORY
Language tag · curated repositories and deep analysis.
Markdown-first shared memory vault for Claude Code and Codex with SQLite, Zvec, Git, closeout, and audit
A free, no-signup, no-API-key Taiwan legal MCP server and CLI with 22.5 million court rulings, administrative interpretations, and constitutional court decisions, plus citation verification. For Claude, ChatGPT, and Codex - bring your own LLM, retrieval-only.
AI-Powered Automate Self-Media Video Generation Tools
Monocle is a framework for tracing GenAI app code. This repo contains implementation of Monocle for GenAI apps written in Python.
Next-gen transparent agent architecture: full behavior auditing, two-stage safe invocation, dual-watermark memory, heartbeat tasks. Reduces P0 incident rate by 80%. Compatible with OpenClaw and the Claude Code skill ecosystem.
A Durex-style copywriting and poster Skill for Claude Code — a two-layer semantic methodology, 8 copywriting formulas, a visual system reverse-engineered from 260 original posters, and an AI image generation / code layout pipeline.
Un-0: an image generator powered by a simulated system of coupled oscillators, an example of an emerging physical computing substrate.
This is a ChatGPT based prompt generation model for MidJorney. The purpose of this model is to simplify the creation of images and increase their creativity. By introducing a partial hint, ChatGPT creates a follow-up that can be used to stimulate creativity and provide new ideas.
From AI tools to TikTok video creation using FFMPEG, Microsoft Edge read aloud and OpenAI Whisper model
PyTorch Implementation of Noise2Noise (Lehtinen et al., 2018)
An MCP server that securely interfaces with your iMessage database via the Model Context Protocol (MCP), allowing LLMs to query and analyze iMessage conversations. It includes robust phone number validation, attachment processing, contact management, group chat handling, and full support for sending and receiving messages.
A WeChat Read (Weread) full-book export tool - uses Playwright and a Canvas hook to extract complete book content as Markdown.
Arknights 24x24 pixel art conversion, manual editing, and auto color-fill tool.
Karpathy LLM based claude harness for PenetrationTesting / Bugbounty using obsidian
Python suite for neuroscience research across all modalities.
A ChatGPT clone built in Reflex
The production-ready agent harness framework for Python
Agent skills for interacting with Railway
Lightweight AI Agent Harness for agentic coding: let strong models explore while humans steer with minimal specs, checkpoints, approval, validation, and reverse sync.
OllamaFreeAPI: Free Distributed API for Ollama LLMs Public gateway to our managed Ollama servers with: - Zero-configuration access to 50+ models - Auto load-balanced across global nodes - Free tier with no API keys required - Built on ollama-python