🌊 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
rUvba230407cb67
diff --git a/v3/CLAUDE.md b/v3/CLAUDE.mdindex a812091c2c..ed5cb2ae77 100644--- a/v3/CLAUDE.md+++ b/v3/CLAUDE.md@@ -21,16 +21,12 @@When the user requests a complex task (multi-file changes, feature implementation, refactoring), **immediately execute this pattern in a SINGLE message:**-```javascript-// STEP 1: Initialize swarm coordination via MCP (in parallel with agent spawning)-mcp__claude-flow__swarm_init({- topology: "hierarchical",- maxAgents: 15,- strategy: "adaptive"-})--// STEP 2: Spawn agents concurrently using Claude Code's Task tool-// ALL Task calls MUST be in the SAME message for parallel execution+```bash+# STEP 1: Initialize swarm coordination via CLI (in parallel with agent spawning)+Bash("npx claude-flow@v3alpha swarm init --topology hierarchical --max-agents 15 --strategy adaptive")++# STEP 2: Spawn agents concurrently using Claude Code's Task tool+# ALL Task calls MUST be in the SAME message for parallel executionTask("Coordinator", "You are the swarm coordinator. Initialize session, coordinate other agents via memory. Run: npx claude-flow@v3alpha hooks session-start", "hierarchical-coordinator")Task("Researcher", "Analyze requirements and existing code patterns. Store findings in memory via hooks.", "researcher")Task("Architect", "Design implementation approach based on research. Document decisions in memory.", "system-architect")@@ -38,7 +34,7 @@ Task("Coder", "Implement the solution following architect's design. Coordinate vTask("Tester", "Write tests for the implementation. Report coverage via hooks.", "tester")Task("Reviewer", "Review code quality and security. Document findings.", "reviewer")-// STEP 3: Batch all todos+# STEP 3: Batch all todosTodoWrite({ todos: [{content: "Initialize swarm coordination", status: "in_progress", activeForm: "Initializing swarm"},{content: "Research and analyze requirements", status: "in_progress", activeForm: "Researching requirements"},@@ -48,13 +44,8 @@ TodoWrite({ todos: [{content: "Review and finalize", status: "pending", activeForm: "Reviewing code"}]})-// STEP 4: Store swarm state in memory-mcp__claude-flow__memory_usage({- action: "store",- namespace: "swarm",- key: "current-session",- value: JSON.stringify({task: "[user's task]", agents: 6, startedAt: new Date().toISOString()})-})+# STEP 4: Store swarm state in memory via CLI+Bash("npx claude-flow@v3alpha memory store --namespace swarm --key current-session --value '{\"task\": \"[user task]\", \"agents\": 6}'")```### 📋 Agent Routing by Task Type