Engram

Engram is a memory server for LLM agents and applications. It provides a REST API and Python SDK that automatically extracts, transforms, and stores memories using vector embeddings and LLM-powered processing.

Use Engram to give your agents persistent memory that they can write to and search across conversations, users, and topics.

• Automatic memory extraction — Send raw text, pre-extracted facts, or full conversations. Engram's pipeline extracts and stores structured memories automatically.
• Semantic search — Find relevant memories using vector similarity, BM25 keyword search, or hybrid retrieval.
• Scoped memory — Isolate memories by project, user, and any custom scope properties (e.g. conversation_id). Topics let you categorize memories within a group.
• Async processing — Memory storage runs asynchronously through a pipeline. Poll run status to track when memories are committed.

Below is an overview of Engram's architecture and information flow:

Your app communicates with Engram through the REST API or Python SDK.

Storing memories: You send content (text, a conversation, or pre-extracted facts) to the API. Engram immediately returns a run_id and processes the content asynchronously through a pipeline:

1. Extract — Pull individual facts from the input.
2. Transform — Deduplicate and merge with existing memories.
3. Commit — Persist the results to the memory store.

You can poll the run_id to check when processing is complete.

Searching memories: You send a query to the API with a retrieval type (vector, BM25, or hybrid). Engram searches the memory store and returns ranked results.

• Quickstart — Create a project, get an API key, store your first memory, and search it.
• Concepts — Understand memories, topics, groups, scoping, and pipelines.
• Guides — Step-by-step instructions for storing, searching, and managing memories.
• REST API reference — Full endpoint documentation with request and response schemas.

Have a question or feedback? Here's how to reach us.