π 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
TypeScript agentic-aiagentic-frameworkagentic-workflowagentsai-agentsai-assistantai-skillsautonomous-agentsclaudecodexdsh-pluginharnessmcp-servermulti-agentmulti-agent-systemsnpmskillsswarmswarm-intelligencetypescript
Checkpoint: File edits
rUv7718b17cb455
diff --git a/README.md b/README.mdindex a1ff31a2ae..9af97c82fd 100644--- a/README.md+++ b/README.md@@ -276,6 +276,201 @@ Claude-Flow v3 is built on rigorous architectural specifications with full traceβββββββββββββββ βββββββββββββββ```+### ποΈ Architecture Diagrams++<details open>+<summary>π <strong>System Overview</strong> β High-level architecture</summary>++```mermaid+flowchart TB+ subgraph User["π€ User Layer"]+ CC[Claude Code]+ CLI[CLI Commands]+ end++ subgraph Orchestration["π― Orchestration Layer"]+ MCP[MCP Server]+ Router[Intelligent Router]+ Hooks[Self-Learning Hooks]+ end++ subgraph Agents["π€ Agent Layer"]+ Queen[Queen Coordinator]+ Workers[54+ Specialized Agents]+ Swarm[Swarm Manager]+ end++ subgraph Intelligence["π§ Intelligence Layer"]+ SONA[SONA Learning]+ MoE[Mixture of Experts]+ HNSW[HNSW Vector Search]+ end++ subgraph Providers["βοΈ Provider Layer"]+ Anthropic[Anthropic]+ OpenAI[OpenAI]+ Google[Google]+ Ollama[Ollama]+ end++ CC --> MCP+ CLI --> MCP+ MCP --> Router+ Router --> Hooks+ Hooks --> Queen+ Queen --> Workers+ Queen --> Swarm+ Workers --> Intelligence+ Intelligence --> Providers+```++</details>++<details>+<summary>π <strong>Request Flow</strong> β How tasks are processed</summary>++```mermaid+sequenceDiagram+ participant U as User+ participant R as Router+ participant H as Hooks+ participant A as Agent Pool+ participant M as Memory+ participant P as Provider++ U->>R: Submit Task+ R->>H: pre-task hook+ H->>H: Analyze complexity++ alt Simple Task+ H->>A: Agent Booster (WASM)+ A-->>U: Result (<1ms)+ else Medium Task+ H->>A: Spawn Haiku Agent+ A->>M: Check patterns+ M-->>A: Cached context+ A->>P: LLM Call+ P-->>A: Response+ A->>H: post-task hook+ H->>M: Store patterns+ A-->>U: Result+ else Complex Task+ H->>A: Spawn Swarm+ A->>A: Coordinate agents+ A->>P: Multiple LLM calls+ P-->>A: Responses+ A->>H: post-task hook+ A-->>U: Result+ end+```++</details>++<details>+<summary>π§ <strong>Memory Architecture</strong> β How knowledge is stored and retrieved</summary>++```mermaid+flowchart LR+ subgraph Input["π₯ Input"]+ Query[Query/Pattern]+ end++ subgraph Processing["βοΈ Processing"]+ Embed[ONNX Embeddings]+ Normalize[Normalization]+ end++ subgraph Storage["πΎ Storage"]+ HNSW[(HNSW Index<br/>150x faster)]+ SQLite[(SQLite Cache)]+ AgentDB[(AgentDB)]+ end++ subgraph Retrieval["π Retrieval"]+ Vector[Vector Search]+ Semantic[Semantic Match]+ Results[Top-K Results]+ end++ Query --> Embed+ Embed --> Normalize+ Normalize --> HNSW+ Normalize --> SQLite+ HNSW --> Vector+ SQLite --> Vector+ AgentDB --> Semantic+ Vector --> Results+ Semantic --> Results+```++</details>++<details>+<summary>π <strong>Swarm Topology</strong> β Multi-agent coordination patterns</summary>++```mermaid+flowchart TB+ subgraph Hierarchical["π Hierarchical (Default)"]+ Q1[Queen] --> W1[Worker 1]+ Q1 --> W2[Worker 2]+ Q1 --> W3[Worker 3]+ end++ subgraph Mesh["πΈοΈ Mesh"]+ M1[Agent] <--> M2[Agent]+ M2 <--> M3[Agent]+ M3 <--> M1[Agent]+ end++ subgraph Ring["π Ring"]+ R1[Agent] --> R2[Agent]+ R2 --> R3[Agent]+ R3 --> R1+ end++ subgraph Star["β Star"]+ S1[Hub] --> S2[Agent]+ S1 --> S3[Agent]+ S1 --> S4[Agent]+ end+```++</details>++<details>+<summary>π <strong>Security Layer</strong> β Threat detection and prevention</summary>++```mermaid+flowchart TB+ subgraph Input["π₯ Input Validation"]+ Req[Request] --> Scan[AIDefence Scan]+ Scan --> PII[PII Detection]+ Scan --> Inject[Injection Check]+ Scan --> Jailbreak[Jailbreak Detection]+ end++ subgraph Decision["βοΈ Decision"]+ PII --> Risk{Risk Level}+ Inject --> Risk+ Jailbreak --> Risk+ end++ subgraph Action["π¬ Action"]+ Risk -->|Safe| Allow[β Allow]+ Risk -->|Warning| Sanitize[π§Ή Sanitize]+ Risk -->|Threat| Block[β Block]+ end++ subgraph Learn["π Learning"]+ Allow --> Log[Log Pattern]+ Sanitize --> Log+ Block --> Log+ Log --> Update[Update Model]+ end+```++</details>+---<details>