🌊 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
rUvb8a2faa3e9ef
diff --git a/AGENTS.md b/AGENTS.mdindex b04b44eb90..a8267d2e1b 100644--- a/AGENTS.md+++ b/AGENTS.md@@ -502,14 +502,30 @@ npx claude-flow mcp start --test### MCP Tools AvailableOnce added, Codex can use these tools via MCP:+**Coordination:**| Tool | Purpose ||------|---------|-| `swarm_init` | Initialize swarm coordination |+| `swarm_init` | Initialize swarm (topology, maxAgents) |+| `swarm_status` | Check swarm state || `agent_spawn` | Register agent roles |-| `memory_store` | Store learning patterns |-| `memory_search` | Retrieve relevant patterns |-| `task_orchestrate` | Coordinate tasks |-| `neural_train` | Train on successful patterns |+| `agent_status` | Check agent state |+| `task_orchestrate` | Coordinate multi-agent tasks |++**Learning & Memory (USE THESE!):**+| Tool | Purpose | When |+|------|---------|------|+| `memory_search` | Semantic vector search | BEFORE every task |+| `memory_store` | Store patterns with embeddings | AFTER success |+| `memory_retrieve` | Get by exact key | When key is known |+| `neural_train` | Train on patterns | Periodic improvement |+| `neural_status` | Check learning state | Debugging |++**Hive Mind (Advanced):**+| Tool | Purpose |+|------|---------|+| `hive-mind_init` | Byzantine consensus swarm |+| `hive-mind_spawn` | Spawn hive workers |+| `hive-mind_broadcast` | Message all workers |### Self-Learning via MCP Tools (PREFERRED)