MCP proxy server for remote HTTP endpoints supporting JSON and Server-Sent Events
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)
AI-first embedded database for LLM agents. Library-first architecture with framework-agnostic tool definitions and MCP adapter.
tegg mcp proxy plugin
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
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
Command-line interface for AgentDB database service
MCPProxy is a Go-based desktop application that acts as a smart proxy for AI agents using the Model Context Protocol (MCP). It provides intelligent tool discovery, massive token savings, and built-in
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)
MCP proxy shim for mcpproxy-go — transforms call_tool_* args_json:string to native args:object. Supports stdio and HTTP Streamable transports.
Persistent, encrypted, and permission-controlled memory for autonomous AI agents.
AgentDB tells you when your agent stops behaving like itself. Causal lineage, time travel and behavioral baselines for any AI agent.
rUv CLI - Agentic Engineering Console with MCP integration
Enterprise-grade AI agent orchestration with WASM-powered ReasoningBank memory and AgentDB vector database (always uses latest agentic-flow)
User-agent database.
Transparent MCP proxy for Stipend — runs Stipend.authorize on every tools/call and forwards to an upstream MCP server.
Core TypeScript library for autonomous cryptocurrency accounting with transaction management, compliance automation, fraud detection, and AgentDB-powered vector search for intelligent financial analysis
Model Context Protocol server for agentic robotics with AgentDB integration
Self-learning portfolio optimization with benchmark swarms and multi-objective optimization
Self-learning energy grid optimization with load forecasting, unit commitment, and swarm scheduling