Engram

Memory infrastructure for AI agents. Store every conversation verbatim. Search by meaning.

Engram is an MCP-native memory server that stores complete, uncompressed conversation transcripts and makes them searchable via semantic search. Connect any MCP-compatible client — Claude Desktop, Claude Code, Cursor, Windsurf, Zed — and your agent remembers everything across sessions.

Quick start

Claude Code

/plugin marketplace add get-engram/engram
/plugin install engram@engram

Restart Claude Code and approve access in the browser. There is no API key to copy and no config file to edit — the server implements the MCP authorization flow (RFC 9728 / 8414 / 7591, PKCE), so the client discovers it, registers itself, and signs you in. A free account is created as part of signing in.

The plugin also ships a skill that tells Claude when to search memory and what is worth saving, so context accumulates without being asked.

Any other MCP client

Point it at the remote server and let OAuth handle access:

{
  "mcpServers": {
    "engram": {
      "type": "http",
      "url": "https://mcp.getengram.app/mcp"
    }
  }
}

For a client that only speaks stdio, bridge to the remote server with mcp-remote — it drives the same browser OAuth flow, so there is still no key to copy:

{
  "mcpServers": {
    "engram": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.getengram.app/mcp"]
    }
  }
}

(An older version of this README suggested npx @getengram/cli mcp; the CLI has no such command and that configuration never worked.)

How it works

• Verbatim storage — every message stored exactly as sent, no summarization or compression
• Semantic search — find relevant context by meaning using bge-base-en-v1.5 embeddings
• MCP-native — speaks the Model Context Protocol natively, works with any compatible client
• Multi-tenant — per-organization isolation, team seats, and API key management

Architecture

Runs entirely on Cloudflare's developer platform:

• Workers — Hono.js API and MCP server
• D1 — SQLite at the edge for messages and metadata
• Vectorize — semantic search index
• Workers AI — embedding generation

Read the full architecture deep-dive.

MCP tools

Engram exposes 6 tools via MCP:

Tool	Description
create_conversation	Start a new conversation with optional title, tags, metadata
append_messages	Add messages to an existing conversation
search	Semantic search across all conversations
get_conversation	Retrieve a conversation with its messages
list_conversations	List conversations with filtering and pagination
delete_conversation	Remove a conversation and its data

See the API reference for full parameters and examples.

Packages

Package	Description
apps/mcp-server	Cloudflare Worker — MCP server and REST API
apps/cli	CLI and MCP bridge (@getengram/cli)
packages/sdk	TypeScript SDK (@getengram/sdk)
packages/db	Database queries and migrations
packages/shared	Shared constants, types, and utilities

Integration guides

• Claude Desktop
• Claude Code
• Cursor
• Windsurf
• OpenAI Codex CLI
• Custom agents

Pricing

Memory is permanent. The limits below are how many messages a plan can hold, not a monthly quota: nothing expires, and deleting conversations frees space.

Plan	Price	Memory
Free	$0	10,000 messages
Pro	$9/mo	1,000,000 messages
Team	$9/seat/mo, minimum 2 seats	1,000,000 messages per seat, pooled
Education	$3/mo per student, $3/seat for academic teams	Pro or Team features with a verified university email
Enterprise	Custom	Unlimited

View pricing

Links

• Website: getengram.app
• Documentation: getengram.app/docs
• Blog: getengram.app/blog
• npm: @getengram/cli

License

Business Source License 1.1 — see LICENSE for details.