agentic-flow and cadre-ai
`ruvnet/agentic-flow` provides infrastructure for deploying Claude-based agents with flexible model switching, which could serve as a deployment platform or complementary component for sophisticated multi-agent systems like `WeberG619/cadre-ai` that leverage specialized Claude agents.
About agentic-flow
ruvnet/agentic-flow
Easily switch between alternative low-cost AI models in Claude Code/Agent SDK. For those comfortable using Claude agents and commands, it lets you take what you've created and deploy fully hosted agents for real business purposes. Use Claude Code to get the agent working, then deploy it in your favorite cloud.
Combines SONA (Self-Optimizing Neural Architecture) with 213 MCP tools and 66 specialized agents using Flash Attention, GNN query refinement, and LoRA fine-tuning for <1ms adaptive learning and 60% cost savings through intelligent model routing. Integrates AgentDB@alpha for graph-based reasoning, multi-agent consensus via 5 attention mechanisms (Flash/Multi-Head/Linear/Hyperbolic/MoE), and background worker dispatch—enabling agents trained in Claude Code to autonomously coordinate and continually learn without catastrophic forgetting.
About cadre-ai
WeberG619/cadre-ai
Your AI agent squad for Claude Code. 17 specialized agents, persistent memory, desktop automation, and a common sense engine.
Builds on Google's Gemini Live API and Agent Development Kit (ADK) with Model Context Protocol (MCP) servers for real-time tool execution via stdio—enabling voice-controlled BIM automation through Revit via named pipes, plus financial analysis and web search. Integrates with Revit 2026 through a dedicated MCP bridge, yfinance/Finnhub for market data, and DuckDuckGo for web queries, with dual deployment modes (local with full Revit support or Cloud Run without desktop automation).
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work