Skip to content

armgit / ruflo

Public Imported from GitHub
0

🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

Checkpoint: File edits

rUvbc12e76dbf1a
diff --git a/README.md b/README.md
index 8a4cbb38c5..3f95da03e0 100644
--- a/README.md
+++ b/README.md
@@ -179,22 +179,22 @@ Claude-Flow v3 introduces **self-learning neural capabilities** that no other ag
| Feature | Claude Flow v3 | CrewAI | LangGraph | AutoGen | MetaGPT |
|---------|----------------|--------|-----------|---------|---------|
-| **Self-Learning** | SONA + EWC++ | πŸ”΄ | πŸ”΄ | πŸ”΄ | πŸ”΄ |
-| **Prevents Forgetting** | EWC++ consolidation | πŸ”΄ | πŸ”΄ | πŸ”΄ | πŸ”΄ |
-| **Expert Routing** | MoE (8 experts) | Manual roles | Graph edges | πŸ”΄ | Fixed roles |
-| **Vector Memory** | HNSW (150x faster) | πŸ”΄ | Via plugins | πŸ”΄ | πŸ”΄ |
-| **Hyperbolic Embeddings** | PoincarΓ© ball model | πŸ”΄ | πŸ”΄ | πŸ”΄ | πŸ”΄ |
-| **Pattern Learning** | From trajectories | πŸ”΄ | πŸ”΄ | πŸ”΄ | πŸ”΄ |
-| **Work Ownership** | Claims system | πŸ”΄ | πŸ”΄ | πŸ”΄ | πŸ”΄ |
-| **Threat Detection** | AIDefence | πŸ”΄ | πŸ”΄ | πŸ”΄ | πŸ”΄ |
-| **Attention Optimization** | Flash Attention | πŸ”΄ | πŸ”΄ | πŸ”΄ | πŸ”΄ |
-| **Low-Rank Adaptation** | LoRA (128x compression) | πŸ”΄ | πŸ”΄ | πŸ”΄ | πŸ”΄ |
-| **Quantization** | Int8 (3.92x savings) | πŸ”΄ | πŸ”΄ | πŸ”΄ | πŸ”΄ |
-| **Consensus Protocols** | 5 (Raft, Byzantine, etc.) | πŸ”΄ | πŸ”΄ | πŸ”΄ | πŸ”΄ |
-| **Background Workers** | 12 auto-triggered | πŸ”΄ | πŸ”΄ | πŸ”΄ | πŸ”΄ |
-| **Multi-Provider LLM** | 6 with failover | 2 | 3 | 2 | 1 |
-| **MCP Integration** | Native | πŸ”΄ | πŸ”΄ | πŸ”΄ | πŸ”΄ |
-| **Swarm Topologies** | 4 (mesh, hierarchical, etc.) | 1 | 1 | 1 | 1 |
+| **Self-Learning** | βœ… SONA + EWC++ | πŸ”΄ | πŸ”΄ | πŸ”΄ | πŸ”΄ |
+| **Prevents Forgetting** | βœ… EWC++ consolidation | πŸ”΄ | πŸ”΄ | πŸ”΄ | πŸ”΄ |
+| **Expert Routing** | βœ… MoE (8 experts) | Manual roles | Graph edges | πŸ”΄ | Fixed roles |
+| **Vector Memory** | βœ… HNSW (150x faster) | πŸ”΄ | Via plugins | πŸ”΄ | πŸ”΄ |
+| **Hyperbolic Embeddings** | βœ… PoincarΓ© ball model | πŸ”΄ | πŸ”΄ | πŸ”΄ | πŸ”΄ |
+| **Pattern Learning** | βœ… From trajectories | πŸ”΄ | πŸ”΄ | πŸ”΄ | πŸ”΄ |
+| **Work Ownership** | βœ… Claims system | πŸ”΄ | πŸ”΄ | πŸ”΄ | πŸ”΄ |
+| **Threat Detection** | βœ… AIDefence | πŸ”΄ | πŸ”΄ | πŸ”΄ | πŸ”΄ |
+| **Attention Optimization** | βœ… Flash Attention | πŸ”΄ | πŸ”΄ | πŸ”΄ | πŸ”΄ |
+| **Low-Rank Adaptation** | βœ… LoRA (128x compression) | πŸ”΄ | πŸ”΄ | πŸ”΄ | πŸ”΄ |
+| **Quantization** | βœ… Int8 (3.92x savings) | πŸ”΄ | πŸ”΄ | πŸ”΄ | πŸ”΄ |
+| **Consensus Protocols** | βœ… 5 (Raft, Byzantine, etc.) | πŸ”΄ | πŸ”΄ | πŸ”΄ | πŸ”΄ |
+| **Background Workers** | βœ… 12 auto-triggered | πŸ”΄ | πŸ”΄ | πŸ”΄ | πŸ”΄ |
+| **Multi-Provider LLM** | βœ… 6 with failover | 2 | 3 | 2 | 1 |
+| **MCP Integration** | βœ… Native | πŸ”΄ | πŸ”΄ | πŸ”΄ | πŸ”΄ |
+| **Swarm Topologies** | βœ… 4 (mesh, hierarchical, etc.) | 1 | 1 | 1 | 1 |
**Key differentiators:**
- **SONA (Self-Optimizing Neural Architecture)** - Learns optimal agent routing from trajectory outcomes with <0.05ms adaptation