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
rUvebff63be9a56
diff --git a/README.md b/README.mdindex c4831b6441..2d952adecf 100644--- a/README.md+++ b/README.md@@ -35,6 +35,8 @@ User β MCP Server β Router β Swarm β Agents β Memory β LLM Providers| **Agents** | 54+ types (coder, tester, reviewer...) | Specialized workers that do the actual tasks || **Intelligence** | SONA, MoE, ReasoningBank | Learns from results to get smarter over time || **Memory** | HNSW index, AgentDB, Cache | Stores patterns and retrieves them 150x faster |+| **Embeddings** | ONNX Runtime, MiniLM | Local vector embeddings without API calls (75x faster) |+| **Fine-tuning** | MicroLoRA, EWC++ | Lightweight model adaptation without full retraining || **Providers** | Anthropic, OpenAI, Google, Ollama | AI models that power agent reasoning || **Learning Loop** | Hooks, Pattern Storage | Feeds results back to improve future routing |