ruflo and agentic-flow

These are complements: ruflo provides the orchestration framework for deploying multi-agent systems, while agentic-flow enables flexible model selection and cost optimization for the agents running within that orchestration.

ruflo
80
Verified
agentic-flow
62
Established
Maintenance 25/25
Adoption 10/25
Maturity 24/25
Community 21/25
Maintenance 10/25
Adoption 10/25
Maturity 17/25
Community 25/25
Stars: 30,017
Forks: 3,322
Downloads:
Commits (30d): 58
Language: TypeScript
License: MIT
Stars: 564
Forks: 131
Downloads:
Commits (30d): 0
Language: TypeScript
License:
No Dependents
No License

About ruflo

ruvnet/ruflo

🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, distributed swarm intelligence, RAG integration, and native Claude Code / Codex Integration

Leverages a Rust-powered WASM kernel for the policy engine and embeddings, with a self-learning architecture that includes elastic weight consolidation, hyperbolic embeddings, and nine reinforcement learning algorithms. Integrates 100+ pre-built specialized agents (coder, tester, reviewer, architect, security) with an automatic task router, consensus mechanisms (Raft/BFT/CRDT), and a retrieval-augmented learning loop that optimizes agent routing over time without manual configuration.

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.

Scores updated daily from GitHub, PyPI, and npm data. How scores work