Skip to content

Latest commit

 

History

History
32 lines (22 loc) · 2.14 KB

File metadata and controls

32 lines (22 loc) · 2.14 KB

Engram : Developer documentation

Engram is an async-first Python SDK that stores agent memory as a Neo4j knowledge graph with LLM-driven extraction (via LiteLLM) and embedding-based recall without LLM calls on the read path.

Resource Link
Repository github.com/hackdavid/engram-memory
Install Clone hackdavid/engram-memory and pip install -e . until PyPI release; then pip install engram-memory-sdk
License MIT

Documentation map

Guide What you will learn
Getting started Install, environment, verify LiteLLM, first ingest / recall
Configuration Config, environment variables, user_id rules, embeddings
API overview Clients, models, exceptions, async vs sync
Production & operations Health checks, engram_memory-e2e, live tests, hooks, logging

The root README remains the high-level product overview, feature list, and full configuration table.

Quick orientation

  1. Ingest — Embed text, vector-search for top-5 similar nodes (slim context: summaries + rel types only), one LLM call for extraction, batched UNWIND writes to Neo4j. Token usage tracked per call.
  2. Recall — Embed query, vector search for seeds, single variable-length Cypher traversal (1 round-trip), composite scoring. Zero LLM calls on the read path.
  3. Isolation — All graph data is scoped by user_id (validated against a configurable regex).

Start with Getting started, then keep Configuration and Production & operations nearby when you deploy.

Additional material

  • overview.md — Early design notes and roadmap (includes non-standard YAML front matter for editor tooling; treat as supplementary, not API contract).