pjlsergeant

byre

--dangerously-skip-permissions, minus your machine.

$ brew install byre
$ cd ~/my-project && byre develop

  No byre.config here — let's set one up (press Enter to accept [default]).
 Template — go node python none [node]:

ruvnet

RuView Soul Signature — passive WiFi biometric identity from hardware (no camera, no wearable). Repo: https://github.com/ruvnet/RuView · Spec: docs/research/soul/

RuView Soul Signature — passive WiFi biometric identity from hardware (no camera, no wearable). Repo: https://github.com/ruvnet/RuView · Spec: docs/research/soul/

Your "Soul Signature" — biometric identity from passive WiFi, no camera, no wearable

Project: RuView / WiFi-DensePose · Date: 2026-05-24 · Spec: docs/research/soul/ in the repo

---

liranhason

Agent Capsule

A pattern for building production AI agents as documents, not agent code.

This document presents the core concept, offering a concise and accessible overview to guide implementation.

The Core Idea

Most production agents are built with an Agent SDK (OpenAI, LangChain, LangGraph, etc.). You write code for tool dispatch, memory, sub-agents, session state, and so on. Every new capability requires a code change and a deployment.

ruvnet

Experiment Output: Pre-Seizure Boundary Detection

Command: cargo run --release -p brain-boundary-discovery Hardware: Apple Silicon (M-series), macOS Rust: 1.92.0 stable, NEON SIMD active

---

karpathy

LLM Wiki

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

The core idea

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.

nhsy

Universal AI Agent Guidelines

This document provides core operating constraints for AI agents. These rules apply across all tasks within this environment.

1. File System & Environment

• Scope: DO NOT write any files outside the project folder.
• Temporary Files: Use .tmp/ within the project root for all temporary files. Ensure this directory is created if it doesn't exist.
• Planning Folder: Use .plans/ within the project root for all development plans. Ensure this directory is created if it doesn't exist.
• Dependency Hygiene: Any new libraries or dependencies must be immediately added to the project's dependency manifests (e.g., pyproject.toml, requirements.txt, package.json) before proceeding with implementation.

gsannikov

Context Manager for Claude Code Agent Teams & Subagents

You are setting up a context management layer for a Claude Code project. Generate the following 4 files exactly as specified, then explain how to use them.

1. Create .claude/commands/context-audit.md

---
description: Audit current context usage across active agents and subagents
---

patyearone

Final Review - Comprehensive PR Review & Testing

Step 0: Determine Review Pass

Before starting, check the git history to determine if this is a follow-up review:

git log --oneline -10 | grep -i "Co-Authored-By: Claude"

graiz

Personal Chief of Staff

The Job

Help [YOUR NAME] execute on what matters without burning out. You are an expert executive admin.

Prioritize, protect time, reduce cognitive load. Make recommendations. Anticipate future needs and potential problems.

dabit3

OpenClaw on DigitalOcean

1. Create a Droplet

Ubuntu 24.04 LTS, nearest region

2. Select Premium AMD

2 GB RAM / 1 AMD CPU / 50 GB NVMe

3. SSH into server