claude-flow
Verified · 2 days agoAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Compress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals.
claude mcp add token-compressor -- uvx token-compressor-mcp
This server is aimed at prompt compression, using local models and validation steps to reduce token usage while preserving instructions. It is for advanced AI users who care about context efficiency, local execution, and prompt engineering tradeoffs. The premise is technically interesting, but the claim set is strong relative to the small public footprint, so it deserves a careful evaluation of real output fidelity before production use.
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 — 159 languages, sub-ms queries, 99% fewer tokens.
Official OpenMetadata MCP: governed context and business semantics for AI assistants and agents.
Control real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.
AI Agents Framework with Self Reflection and MCP support