REA
Verified · 35 days agoReverse engineer anything from your terminal or agent with one CLI and MCP server.
Context GC for LLM agents: offload large tool outputs and recall them to save tokens.
claude mcp add lethe -- uvx lethe-llm-context
This server is designed to offload large tool outputs and recall them later, effectively acting as context garbage collection for LLM agents. It is for developers trying to reduce token pressure in long-running agent sessions rather than end users looking for a standalone integration. The idea is relevant, but this kind of memory layer depends heavily on retrieval behavior and implementation details, so it feels experimental until there is broader adoption or clearer maintenance history.
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.