Cartisien/engram-mcp

Overview

Provides a persistent semantic memory layer for AI agents via the Model Context Protocol (MCP). Built in TypeScript, it integrates with the @cartisien/engram system to store and recall knowledge across sessions.

Best for

Best for
Developers building AI agents that need reliable, long-term semantic memory

Use cases

• Give AI agents long-term memory of prior conversations
• Enable agents to store and retrieve facts or preferences
• Build context-aware tools that don't reset on each invocation

Notes

Provides a persistent semantic memory layer for AI agents via the Model Context Protocol (MCP). Built in TypeScript, it integrates with the @cartisien/engram system to store and recall knowledge across sessions.

0 stars on GitHub. Last updated 2026-04-20. Licensed MIT.

Use cases

• Give AI agents long-term memory of prior conversations
• Enable agents to store and retrieve facts or preferences
• Build context-aware tools that don’t reset on each invocation

Pros

• Standard MCP interface simplifies integration
• Persistence keeps agent context across restarts
• Written in TypeScript for type safety

Cons

• Relies on @cartisien/engram as an external dependency
• No community metrics (0 stars) to indicate adoption or stability
• Limited documentation outside the repo itself

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.