Self-learning vector memory for AI agents — single-file .rvf cognitive container with HNSW search, episodic Reflexion memory, causal graph + Cypher, 9 RL algorithms, Thompson Sampling bandit, 41 MCP tools, hybrid (BM25 + dense) retrieval, GNN attention. 1

Memory module - AgentDB unification, HNSW indexing, vector search, hybrid SQLite+AgentDB backend (ADR-009)

JavaScript SDK for AgentDB database service

Memory module - AgentDB unification, HNSW indexing, vector search, hybrid SQLite+AgentDB backend (ADR-009)

AgentDB with optimized ONNX embeddings - 100% local, GPU-accelerated AI agent memory

Memory module - AgentDB unification, HNSW indexing, vector search, hybrid SQLite+AgentDB backend (ADR-009)

Command-line interface for AgentDB database service

AgentDB v3 - Intelligent agentic vector database with RVF native format, RuVector-powered graph DB, Cypher queries, ACID persistence. 150x faster than SQLite with self-learning GNN, 6 cognitive memory patterns, semantic routing, COW branching, and compreh

Model Context Protocol server for agentic robotics with AgentDB integration

Standalone MCP server with agentic-flow and agentdb integration

Core TypeScript library for autonomous cryptocurrency accounting with transaction management, compliance automation, fraud detection, and AgentDB-powered vector search for intelligent financial analysis

AI agent coordination for Jujutsu VCS with quantum-ready architecture, QuantumDAG consensus, AgentDB learning, and zero-dependency deployment

Memory module - AgentDB unification, HNSW indexing, vector search, hybrid SQLite+AgentDB backend (ADR-009)

Enterprise-grade AI agent orchestration with WASM-powered ReasoningBank memory and AgentDB vector database (always uses latest agentic-flow)

Self-learning vector memory for AI agents — single-file .rvf cognitive container with HNSW search, episodic Reflexion memory, causal graph + Cypher, 9 RL algorithms, Thompson Sampling bandit, 41 MCP tools, hybrid (BM25 + dense) retrieval, GNN attention. 1

MCP server for AgentDB - Search and contribute to the AI agent knowledge base

Production-grade E2B sandbox orchestration with agentic-flow swarms and AgentDB caching for distributed AI agent execution

Memory module - AgentDB unification, HNSW indexing, vector search, hybrid SQLite+AgentDB backend (ADR-009)

Self-learning vector memory for AI agents — single-file .rvf cognitive container with HNSW search, episodic Reflexion memory, causal graph + Cypher, 9 RL algorithms, Thompson Sampling bandit, 41 MCP tools, hybrid (BM25 + dense) retrieval, GNN attention. 1

DSPy.ts 2.0 - Advanced declarative AI framework with multi-agent orchestration, self-learning capabilities, and state-of-the-art optimizers. Powered by AgentDB, ReasoningBank, and Swarm architecture.