Engram

What is Engram?

Engram is a universal AI memory backend that gives any AI model a persistent, growing brain.

It stores memories in a local SQLite database with full-text search, vector semantic search, and a knowledge graph that connects related concepts.

Memory Types

• Episodic — past events, conversations, decisions
• Semantic — facts, knowledge, and beliefs about the world
• Procedural — how-to instructions, workflows, and code patterns

Key Features

• Semantic search — find memories by meaning, not just keywords
• Knowledge graph — 7-step graph traversal connects related memories
• Contradiction detection — automatically flags conflicting beliefs
• Local-first — all embeddings run on-device, no API keys needed, no data leaves your machine
• Universal — works with Claude, OpenAI, Ollama, and any MCP-compatible client

Install

npx -y @engram-ai-memory/mcp@latest

Claude Desktop Config

{
  "mcpServers": {
    "engram": {
      "command": "npx",
      "args": [
        "-y",
        "@engram-ai-memory/mcp@latest"
      ]
    }
  }
}

18 MCP Tools

store_memory, search_memory, recall_context, add_knowledge, check_contradictions, resolve_contradiction, forget, tag_memory, list_tags, decay_sweep, decay_policy, re_embed, embedding_status, index_status, memory_stats, plugin_list, webhook_subscribe, webhook_list

Links

• Homepage: https://engram.am
• GitHub: https://github.com/ayvazyan10/engram
• npm: https://www.npmjs.com/package/@engram-ai-memory/mcp