Atlas - Cognitive Memory
Atlas gives AI agents persistent, queryable memory — the same way the human brain stores different kinds of information in different ways. Most “AI memory” solutions are a single vector collection. Atlas implements the full cognitive memory stack across three layers:| Layer | Store | What it remembers |
|---|---|---|
| Episodic | Qdrant (vector) | Raw experiences — what happened, verbatim |
| Semantic | Neo4j (graph) | Structured facts — entities, relations, ownership |
| Working | Redis (cache) | Session context — what was said 5 messages ago |
Why not just stuff context into the prompt?
Prompt-stuffing doesn’t scale:- Token limits force you to truncate, losing older facts
- All facts are weighted equally — a stale fact competes with a fresh one
- No concept of which facts are still true
- Cost grows linearly with memory size
The scoring function
Every retrieval is ranked by a hybrid score using following parameters:| Symbol | Signal | Default weight |
|---|---|---|
| V | Semantic similarity to your query | 0.20 |
| R | Recency (exponential decay) | 0.70 |
| F | Access frequency | 0.10 |
| A | Graph relation alignment | 0.50 |
What you can build
- Support agents that remember every ticket, preference, and resolution
- Research assistants that accumulate knowledge across sessions
- B2B SaaS agents with fully isolated memory per customer namespace
- Coding agents that remember architecture decisions and tech choices
- Personal AI that learns your preferences over time
Base URL
https://api.atlas.bsyncs.com All endpoints require anX-API-Key header. Get yours at
atlas.bsyncs.com/signup.