Engram Rs
Hierarchical memory for AI agents. Three-layer (buffer/working/core) with automatic decay, promotion, and semantic search.
Overview
Engram gives AI agents persistent, human-like memory. Memories flow through three cognitive layers — buffer (short-term), working (active knowledge), and core (long-term) — with automatic decay, promotion, and consolidation.
Features:
- Semantic search via HNSW vector index
- Automatic deduplication and merging
- Namespace isolation for multi-agent setups
- Session context extraction from LLM conversations
- MCP protocol support (stdio transport)
- Local-first, single-binary Rust server + SQLite
Works with Claude Desktop, Cursor, Windsurf, and any MCP-compatible client.
Server Config
{
"mcpServers": {
"engram": {
"command": "npx",
"args": [
"-y",
"engram-rs-mcp"
],
"env": {
"ENGRAM_URL": "http://localhost:3917",
"ENGRAM_API_KEY": "",
"ENGRAM_NAMESPACE": ""
}
}
}
}Project Info
Created At
3 months agoUpdated At
3 months agoAuthor Name
kael-bitStar
-Language
-License
-Recommend Servers
View AllAmap Maps
@amap
高德地图官方 MCP Server
a year ago
Serper MCP Server
@garymengcom
A Serper MCP Server
Python
a year ago
Shotapi
@smallhandsome
a day ago
虎嗅嗅 Ai行业参谋
5 hours ago
Test
@modelcontextprotocol
test
6 months ago
Fabric
@fabric-agent-plugins
3 hours ago