Free local OSS premortem, self-heal, and no-spend Golden Loop readiness CLI for plans, launches, and installable AI agent repositories.

Failure-first spec stress test — inverts sycophancy to surface failure modes (C2/P1).

A QA auditor and test-scaffolding engine for AI-generated codebases. Finds what the model did not test, ranks it by what actually breaks, and writes the tests.

An open-source prospective hindsight simulation engine utilizing the Gary Klein premortem method powered by Gemini.


Tempered judgment your agent can install. Expert skills for AI agents.

MCP server that exposes Mneme to Claude Code, Cursor, Continue, and other AI clients

Ready-made workflows assembled from the spendgraph packages.

Bootstrap Claude Code configuration in any repository: install the plugins, skills, and commands you want, declaratively and reproducibly.

OMNIMIND - Infinite Dimensional Thinking System with MCP - Cross-platform (Android/Linux/Mac/Windows)

The open source AI strategy agent

Durable evidence-backed deliberation and Decision CI MCP server

A deliberately-small, layered skills + agents framework for Claude Code. Install skills, session memory, and a multi-agent task runtime into any project.

Make your clanker your investing analyst. A personal research companion that learns your edges and stress-tests your ideas against the investing canon.

Your AI product operating system — by Mind the Product

mindit — AI skills that find the design decisions you didn't make. Eight forces, eleven skills, scored output. v2 adds a CLI, MCP server, and decision-graph linter.

A fast yes/no reflection CLI to surface the side-effects of a change before you make it. Scans your project (frontend/backend/full-stack) and asks stack-relevant questions. Think before you touch the big app.

FAILSAFE: 1-3 risk pre-mortem protocol — linter, schema, spec, and HTML renderer.

MCP server for systematic thinking, mental models, debugging approaches, and memory management