Documentation

# npm
npm install -g engram-sdk && engram init

# or Homebrew
brew tap tstockham96/engram && brew install engram-sdk
engram init

npm install -g engram-sdk
export GEMINI_API_KEY=your-key-here
npx engram-serve
# ✓ Engram API listening on http://127.0.0.1:3800

import { Vault } from 'engram-sdk';

const vault = new Vault({
  owner: 'my-agent',
  dbPath: '~/.engram/my-agent.db'
});

// Store — entities & topics extracted automatically
await vault.remember('User prefers TypeScript over Python');

// Recall — semantic search + spreading activation
const memories = await vault.recall('What languages does the user like?');
console.log(memories[0].content);
// → "User prefers TypeScript over Python"

// Consolidate — distill episodes into knowledge
const report = await vault.consolidate();
console.log(`Created ${report.semanticMemoriesCreated} semantic memories`);

// Briefing — structured summary for session start
const briefing = await vault.briefing();

// Stats
const stats = vault.stats();
console.log(`${stats.total} memories, ${stats.entities} entities`);

engram init                  Set up for Claude Code / Cursor / MCP clients
engram mcp                   Start the MCP server (stdio transport)
engram remember <text>       Store a memory
engram recall <context>      Retrieve relevant memories
engram stats                 Show vault statistics
engram entities              List known entities
engram consolidate           Run memory consolidation
engram forget <id> [--hard]  Forget a memory
engram search <query>        Full-text search
engram export                Export entire vault as JSON
engram eval                  Health report & value assessment
engram repl                  Interactive REPL mode
engram hosted                Start the multi-tenant hosted server

Options:
  --db <path>       Database file path
  --owner <name>    Owner identifier
  --agent <id>      Agent ID for source tracking
  --json            Output as JSON