engram
Hierarchical memory for AI agents. Three-layer (buffer/working/core) with decay and promotion.
Open the source (opens github.com) https://github.com/kael-bit/engram-rs
Before you use it
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
- Needs credentials: ENGRAM_API_KEY. Use a key with the least access you can.
What it is
MCP servers from io.github.kael-bit.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
npm package (stdio)
engram-rs-mcp@0.10.0
From the server's entry in the official MCP Registry
Settings it asks for
ENGRAM_URL· URL of the engram serverENGRAM_API_KEYsecret · API key for authentication
Related
-
engram-server
MCP serversDurable memory for AI agents: fact extraction, hybrid retrieval, temporal graph. SQLite/Postgres.
ghcr.io/jamjet-labs/engram-server:0.5.0 -
EngrAmo
MCP serversCreate and study EngrAmo spaced-repetition flashcards from your AI client.
@engramo/mcp@1.3.5 -
engram
MCP serversMCP adapter for Engram - organizational memory for AI agents
@spectra-g/engram-adapter@0.2.11 -
Engram
MCP serversMemory for AI agent teams across tools, sessions, repositories, and teammates.
engram-tools@0.4.11 -
Engramic
MCP serversYour organisation's decisions, goals and constraints, with the reasoning, for every agent.
-
engram
MCP serversIntelligent agent memory with automatic extraction, consolidation, and bi-temporal recall.
engram-sdk@0.5.1