Benchmarks
The numbers that matter in production.
Under the hood
Why not just a RAG or vector DB?
A vector DB answers "what words are most similar?" A memory engine answers "what's true right now?" Those are different queries, and they need different data structures.
Dimension
Naive RAG
"what words are most similar?"
XTrace Memory
"what's true right now?"
✕
✓
✕
✓
✕
✓
✕
✓
Integration
✕
✓
How it works
One write. One recall.
A belief engine in the middle.
Click a node on the timeline to see how memory builds up with XTrace
use cases
Our memory is the difference between an agent and a chatbot.
Support agents
Know the user's plan, their last three tickets, and the policy changes since they signed up. Stop asking "what's your order number?"
Coding agents
Remember which patterns this repo favors, what conventions were deprecated last month, and which files the user owns.
Voice agents
<80ms p50 is the latency budget you need. Facts-only recall means short prompts — fewer tokens, lower cost, faster TTFB.
Research agents
Track what's been read, what's been ruled out, and which claims are still load- bearing. Supersede chains = reproducible research.
Companions
Users want an AI that actually knows them. Not one that forgot their dog's name between sessions.
Workflow / ops agents
Long-running agents that span days and tools. Lineage matters here more than anywhere, XTrace Memory gives you audit + replay.
Same engine, two surfaces
Most Memory API customers ship their agent, then roll memory out to the rest of the team. That's Memory Hub: the same belief engine, surfaced as a product humans can use.
you are here
Memory API
Memory for your agent
A drop-in SDK. Your code, your agent, your stack. One engine per application.
·
Typescript SDK and API
·
Belief-revision based long term memory system
·
Scoped per agent · per user · per group
·
Competitive pricing