Side-by-side comparison of two Model Context Protocol servers — install paths, tools, quality signals, and directory engagement so you can pick the right one for Claude, Cursor, and other MCP clients.
Structured planning, parallel execution in git worktrees, and deep validation for Claude Code. Turns a one-line objective into a validated DAG of modules executed by worker agents, each self-checked and cross-module-reviewed before merge-back. 7 MCP tools: validate, validateplan, memoryrecall, memorysave, iterationstate (per-run scoped, with stagnation/velocity/oscillation detection), forgelogs, sessionstate. Stdio-only. Zero telemetry.
Multi-LLM deliberation with anonymized peer review. Runs a 3-stage council: parallel responses → anonymous ranking → synthesis. Based on Andrej Karpathy's LLM Council concept.