Skip to main content

What is Atlas?

Atlas is a production-grade memory backend for AI agents. Instead of losing context between conversations or cramming everything into a single prompt, Atlas gives your agents three distinct, interconnected memory stores that mirror how human memory actually works.

Episodic Memory

Stores raw conversation chunks as vector embeddings in Qdrant. Enables fast similarity search over past experiences.

Semantic Memory

Extracts entities and relationships into a Neo4j knowledge graph. Supports multi-hop reasoning across facts.

Working Memory

A per-session sliding context cache in Redis. Tracks rolling topic vectors, recent entities, and hot facts.

How it works

When you call brain.add("Sarah is the Lead Engineer at Acme Corp."), Atlas:
  1. Chunks the text using a semantic chunker (embedding-aware sentence grouping)
  2. Extracts named entities and relationships via LLMGraphTransformer or spaCy
  3. Stores vector embeddings in Qdrant (episodic) and graph triples in Neo4j (semantic)
  4. Updates the session topic vector in Redis (working memory)
When you call brain.search("Who manages engineering at Acme?"), Atlas:
  1. Runs hybrid retrieval across all three stores simultaneously
  2. Scores results vector similarity, recency, frequency, graph strength
  3. Returns ranked, de-duplicated facts ready to inject into your LLM system prompt

Key features

Ask complex relational questions across up to 5 hops in the knowledge graph. Atlas traverses entity relationships and grounds LLM answers in retrieved facts — no hallucination.
Memories decay over time via the Ebbinghaus forgetting curve. Consolidation compresses related clusters into abstractions. Pruning removes low-confidence nodes below a configurable threshold.
Every memory write and read is scoped to a user_id derived server-side from your API key. No cross-tenant leakage is possible — even if a client sends the wrong user_id.
The atlas-mem package requires only requests. Async support via httpx is available as an optional extra.

Pricing & tiers

TierMonthly OpsBatch SizeGraph QAPrune
Free1,0005
Starter50,00020
Pro500,00050
Scale5,000,000100
EnterpriseUnlimited100
Operation costs: ingest = 5 ops, retrieve = 2 ops, graph_qa = 10 ops, consolidate = 3 ops, prune = 1 op, stats/health = free.

Next steps

Quickstart

Be up and running in under 5 minutes.

API Reference

Full endpoint documentation with request/response schemas.