What is Waggle MCP ?
Waggle MCP is an open-source AI memory tool that gives large language models persistent, graph-structured memory through a Model Context Protocol (MCP) server. Instead of losing context between sessions, it stores decisions, facts, preferences, and their relationships as typed nodes and edges in a local knowledge graph, so AI agents can recall and build on prior work across projects. Waggle MCP uses hybrid retrieval that combines vector search, BM25 keyword matching, and graph traversal to surface the most relevant context, and it supports temporal queries for point-in-time lookups and conflict resolution across sessions. It is local-first by default, running on SQLite with no cloud calls or API keys required, and automatic ingestion hooks capture conversational turns to extract durable information. Installation is a one-liner via pipx, and a single setup command detects MCP clients and configures memory hooks; a doctor command verifies the install. Waggle MCP works across MCP-compatible clients including Claude, Cursor, Codex, and Gemini CLI, making it a portable persistent-memory layer for developers building long-running AI agents that need decision continuity.
What is Waggle MCP used for?
Developers building long-running AI agents use Waggle MCP to give LLMs persistent, graph-structured memory that survives across sessions and MCP clients.
How much does Waggle MCP cost?
Pros and cons
Pros
• Gives LLMs persistent, graph-structured memory through an MCP server • Stores decisions, facts, preferences, and relationships as typed nodes and edges • Hybrid retrieval combines vector search, BM25 keyword matching, and graph traversal • Supports temporal queries for point-in-time lookups and cross-session conflict resolution • Local-first on SQLite with no cloud calls or API keys required; installs via a pipx one-liner
Cons
• Aimed at developers, so setup assumes command-line and MCP familiarity • Local-first SQLite design is single-machine rather than shared across a team by default • Automatic ingestion quality depends on how well durable information is extracted • Younger project than some established memory layers like Mem0 or Zep
Questions about Waggle MCP
What is Waggle MCP?
It is an open-source MCP server that gives large language models persistent, graph-structured memory, storing decisions, facts, preferences, and their relationships as typed nodes and edges in a local knowledge graph.
How does Waggle MCP retrieve relevant context?
It uses hybrid retrieval that combines vector search, BM25 keyword matching, and graph traversal, and it supports temporal queries for point-in-time lookups and conflict resolution across sessions.
Does Waggle MCP need cloud access or API keys?
No. It is local-first by default, running on SQLite with no cloud calls or API keys required.
How do I install Waggle MCP?
Installation is a one-liner via pipx, and a single setup command detects MCP clients and configures memory hooks, with a doctor command to verify the install.
Which AI clients does Waggle MCP work with?
It works across MCP-compatible clients including Claude, Cursor, Codex, and Gemini CLI, making it a portable persistent-memory layer.
What are the best alternatives to Waggle MCP ?
Mem0, Zep, Letta (MemGPT), Cognee, Graphiti
Reviews
Sign in to rate and review Waggle MCP .
Sign in to reviewNo reviews yet. Be the first to review Waggle MCP !