claude-flow
Verified · 2 days agoAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Agent-first cognitive substrate: 20 verbs + 50 lint dims over a self-validating graph.
A persistent memory and self-evolution layer an agent inhabits over MCP: between turns it ingests conversation material into tamper-evident history, distills it into durable understanding, and prunes stale state, aiming to carry one relationship across model generations. There is real code here — a Rust substrate, Python kernel, and tested MCP boundary — but the README is manifesto more than documentation ('living fungal armor'), it is v0.9 alpha built from source by a single author, and its star count traces to a mid-April wave from Chinese dev communities rather than sustained adoption. For the philosophically curious, not production.
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