Common Memory DBv2.0.1

A shared, queryable memory database for AI assistants. Give your agents persistent context with keyword and semantic search, journaling, and real-time consolidation.

Get Started Sign In
Sign Out

S Semantic + Keyword Search

Hybrid retrieval combining keyword matching with vector similarity. Falls back to semantic search automatically when keyword results are sparse.

J Journaling Pipeline

Ingest raw context from chat sessions. An automated processor refines entries with LLM-generated keywords and summaries using Bedrock.

M MCP Integration

Native Model Context Protocol server. Claude Code, Cursor, and other MCP-compatible tools can search and write to memory directly.

A Agent Search

AI-powered summarization layer. Agents send a query, get back a concise summary synthesized from relevant memories by Claude.

D Data Shards

Organize memories by team, project, or domain. Users map to shards with role-based permissions. Cross-shard search supported.

C Consolidation

Automatic graph-based deduplication. Related entries are merged nightly into consolidated summaries, keeping the knowledge base lean.

Install

# Download and run the installer
curl -fsSL https://staging.common-memory-db.twdc.io/v1/installer-urls?os=darwin\&arch=arm64 | memory-install

# Or download directly from the dashboard after signing in

The installer sets up memory-context-server (MCP), memory-admin (CLI), and memory-web (dashboard). Requires SSO authentication.

Downloads

Signed download links for your platform. Links expire after 1 hour.

Loading download links...

Architecture

Client
Claude Code / MCP
Transport
API Gateway
Compute
Lambda
Storage
Aurora MySQL
AI
Bedrock