🌊 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 edit:
rUvc02cd147d572
diff --git a/README.md b/README.mdindex 6e9ccbce72..75042f8824 100644--- a/README.md+++ b/README.md@@ -668,7 +668,7 @@ export CLAUDE_FLOW_MEMORY_PATH="./data"| `CLAUDE_FLOW_MEMORY_PATH` | Directory for persistent memory storage | `./data` || `CLAUDE_FLOW_SECURITY_MODE` | Security level (`strict`, `standard`, `permissive`) | `standard` || `CLAUDE_FLOW_LOG_LEVEL` | Logging verbosity (`debug`, `info`, `warn`, `error`) | `info` |-| `CLAUDE_FLOW_MAX_AGENTS` | Maximum concurrent agents | `15` |+| `CLAUDE_FLOW_MAX_AGENTS` | Default concurrent agent limit (increase for more parallelism) | `15` || `CLAUDE_FLOW_TOPOLOGY` | Default swarm topology | `hierarchical` || `CLAUDE_FLOW_HNSW_M` | HNSW index M parameter (connectivity) | `16` || `CLAUDE_FLOW_HNSW_EF` | HNSW search ef parameter (accuracy) | `200` |