A curated list of resources about Ralph, the AI coding technique that runs AI coding agents in automated loops until specifications are fulfilled.

From thought to skill. From signal to structure.

Self-hosted agent OS with skills, workflows, MCP, and second brain storage.

Transform YouTube videos into a compounding knowledge base with transcripts, vision analysis, and agentic search. Works as an MCP server for Claude, Copilot & more.

Agentic personal OS to automate high-leverage workflows with Codex, Claude Code, Pi, OpenClaw and other coding agents/ runtime platforms.

Where AI agents hire AI agents — hiring and coordination infrastructure for the agent economy

🐬DeepChat - A smart assistant that connects powerful AI to your personal world

YouTube Transcript API skills for AI agents. Get transcripts, search videos, browse channels. Works with OpenClaw, Hermes Agent, and other agent runtimes.

Turn any website into a compact CLI tailored for AI agents. Browse the web in hundreds of tokens, not tens of thousands.

30 sec to give your AI agents persistent memory. Reduce 90% token consumption while also maintaining quality.

Learn Anything is an AI-powered recursive learning system — Socratic deep-dives and TDD-style exercises integrated directly into your coding assistant.

Curated list of Agent Skills for AI coding agents like Claude Code, Codex and Cursor.

Causal memory layer for AI agents — MCP server that records decision→outcome relationships. Survives compaction.

Production agent skills for Claude Code, Cursor, and any SKILL.md harness — Codex fleets, video pipeline, monorepo review bundles, multi-chain explorer.

InferSports Agent Skill — live Asian-priced football & basketball odds + scores. Read-only, keyless. Claude Code / Codex / OpenClaw.

Use ChatGPT Web (including Pro) as a native model in Codex — with context, tools, streaming and images, without using Codex quota.

Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support

Official Microsoft Learn MCP Server and CLI tool – powering LLMs and AI agents with real-time, trusted Microsoft docs & code samples.

turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.

Samurai-inspired multi-agent system for Claude Code. Orchestrate parallel AI tasks via tmux with shogun → karo → ashigaru hierarchy.

Every past session, subagent, and workflow -- queryable by your agent, browsable by you

Discover and compare open-source Agent Skills, tools & MCP servers — with quality scoring, trending analysis, and automated GitHub sync

Zero-configuration MCP server that unifies multiple AI coding assistants (Codex, Claude Code, Cursor, Gemini) through intelligent auto-discovery and standardized interface

Open-World Self-Evolution for LLM Agents — agents that build both their skills and their own verification signals from scratch, with no target-task supervision. (Code coming soon.)