REA
Verified · 33 days agoReverse engineer anything from your terminal or agent with one CLI and MCP server.
Verified memory for coding agents: claims cited against code, stale withheld, savings receipts.
claude mcp add kage -- npx -y @kage-core/[email protected]
A memory layer for coding agents with a genuinely interesting angle: every stored claim is cited against actual code, and memories go stale-and-withheld when the code they reference changes — deterministic checks, stored as plain files in your repo, no account needed. It builds on Google's (real) Open Knowledge Format and ships a working CLI, viewer, and installer. Treat the traction numbers with salt, though: ~1,200 npm downloads a week doesn't square with 23 stars, zero watchers, and an org nobody follows — heavy version churn (72 releases in eleven weeks) and launch-day spikes explain more of it than adoption does, and the README's zero-dependencies badge is contradicted by the package's five dependencies. Young and single-vendor, but the substance is real.
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Agent teams, swarms, memory and hooks for Claude Code and Codex, served over MCP.
AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Draw and visually collaborate with your agents on tldraw's canvas.
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Keyword research, site audits, rank tracking and AI visibility for your AI agent.