AgentDB Advanced Features

Configure QUIC synchronization, hybrid search, and multi-database management for AgentDB vector stores.

Updated Aug 18, 2026
One-click install
npx skills add https://github.com/wandreandrade2018-maker/claude-config --skill agentdb-advanced-features-wandreandrade2018-maker
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: AgentDB Advanced Features
Source: https://github.com/wandreandrade2018-maker/claude-config/tree/main/.claude/skills/agentdb-advanced
Command: npx skills add https://github.com/wandreandrade2018-maker/claude-config --skill agentdb-advanced-features-wandreandrade2018-maker

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires agentdb, agentic-flow.

What problem does it solve? Building distributed AI systems with vector databases requires solving cross-node synchronization, redundant search results, and metadata filtering challenges that basic vector search setups cannot handle. ## Core Features & Use Cases - QUIC Synchronization: Synchronize AgentDB instances across network nodes with sub-millisecond latency, multiplexed streams, and TLS 1.3 encryption. - Hybrid Search: Combine vector similarity with metadata filters (price ranges, categories, dates) and weighted scoring for precise retrieval. - Multi-Database Management & MMR: Shard databases by domain, apply Maximal Marginal Relevance for diverse results, and synthesize context from multiple memories. - Use Case: Deploy a three-node AgentDB cluster where learned patterns replicate across peers in ~1ms, then run hybrid searches that filter research papers by year, category, and citation count while ranking by semantic similarity. ## Quick Start Set up AgentDB with QUIC synchronization enabled across two peers and run a hybrid vector search filtered by metadata.

Frequently Asked Questions about AgentDB Advanced Features

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I enable QUIC synchronization between AgentDB instances?

Enable QUIC sync by setting enableQUICSync to true in createAgentDBAdapter, specifying a syncPort and a list of syncPeers. Alternatively, set the AGENTDB_QUIC_SYNC, AGENTDB_QUIC_PORT, and AGENTDB_QUIC_PEERS environment variables before starting each node.

How to combine vector similarity with metadata filters in AgentDB?

Use retrieveWithReasoning with a filters object supporting operators like $gte, $lte, $in, and $contains alongside the query embedding. You can also set hybridWeights to balance vector similarity against metadata match scores.

Which distance metric should I use for vector search?

Cosine similarity suits text embeddings and semantic search, euclidean distance fits spatial data and image embeddings, and dot product works best for pre-normalized vectors. Choose based on whether vector magnitude matters for your data.

Why is AgentDB QUIC sync not working between nodes?

QUIC sync commonly fails because the firewall blocks UDP traffic on port 4433. Allow the port with your firewall tool, verify peers are reachable via ping, and run with DEBUG=agentdb:quic to inspect sync logs.

What does MMR do in vector search results?

MMR (Maximal Marginal Relevance) diversifies retrieved results to reduce redundancy. The mmrLambda parameter controls the trade-off: 0 maximizes relevance, 1 maximizes diversity, and 0.5 provides a balanced default.