THE PROBLEM
The context window is an agent's only built-in memory. When the session closes, so does everything it learnt.
A vector store appends. When a fact changes, both versions score well and nothing says which won, so the model guesses.
Retrieval plus an LLM call on every question charges the same for a lookup as for real reasoning.
Agent Memory is not
a vector database
a chat-history blob
a hand-rolled knowledge graph
a context-window manager
an agent runtime
It is one database holding every fact your agent learns, with its source, its corrections and its history.
HOW IT WORKS
Most memory layers leave reconciliation to application code. Here it is part of the engine.
Conversations and documents become typed entities, attributes and relations, each row carrying its source, span and confidence.
One reconciler decides what a new fact does to an old one: corrections supersede, and disagreement below the floor is recorded as uncertainty.
A question leaves by the cheapest tier that can answer it. Where retrieval runs, eight signals fuse into one ranking.
THE COST LADDER
Cheap questions are cheap. Expensive questions are explicit.
Tier 1
Direct lookup
The question resolves to a structured query over typed facts, and the answer comes straight from the store.
Tier 2
Response reuse
Entity-aware invalidation: a cached answer is dropped the moment a fact it cited is superseded, so a hit is never stale.
Tier 3
Hybrid retrieval
Eight signals fused into one ranking, then synthesis. Per-signal scores are recorded with the answer.
Tier 4
Full-context fallback
The expensive path, taken deliberately rather than by default.
Bar length is how far a question walks the ladder, not a measured cost. Every query records the tier that answered it.
HOW IT BEHAVES
Session 4 · turn 42
Facts written
Tobie works at Acme as CTO
turn:42 · bytes 15-38 · confidence 0.91
Acme is an organisation
turn:42 · bytes 34-38 · confidence 0.95
Session 9 · turn 43
Facts after reconciliation
Tobie works at Acme as CTO
superseded · valid_until 2026-04-12 · row retained
Tobie works at SurrealDB
turn:43 · bytes 12-30 · confidence 0.88
Ask · today
Where does Tobie work?
SurrealDB
cited turn:43
Ask · as of 2026-04-01
Where does Tobie work?
Acme, as CTO
cited turn:42 · superseded 2026-04-12
INTEGRATIONS
Seven MCP tools over streamable HTTP, fourteen agent frameworks and eight SDKs, on one REST surface.
PRICING
Free, no card needed
Choose Sandbox if you:
Key features:
Billed monthly
Choose Lite if you:
Key features:
Billed monthly
Choose Standard if you:
Key features:
Billed monthly
Choose Plus if you:
Key features:
Annual agreement
Choose Enterprise if you:
Key features:
Features
Sandbox
Lite
Standard
Plus
Enterprise
Plans and usage
Free
$30
$300
$1,100
Custom
3 million (one-off)
1 million
10 million
40 million
Agreed with sales
Not available
Overage rates apply
Overage rates apply
Overage rates apply
Agreed with sales
Memory capabilities
Isolation and security
Qualifying engagements
Support
THE PLATFORM
Database
Document, graph, vector, time-series and relational in one engine.
Agent Memory
What an agent learns, with its source and its time, in the same engine.
Cloud
Managed clusters in the regions you choose, scaled on demand.
Studio
Query, explore and design the schema from the browser.
MCP
Every model that speaks MCP reaches the database and the memory directly.
IN PRODUCTION
14,000+
Developers building on SurrealDB Cloud
4M+
Developers building on SurrealDB worldwide
FROM THE TEAMS
SurrealDB gives us a foundation where we can unify semantic search, knowledge graphs, and AI-driven decision making without stitching together multiple systems. Collapsing responsibility into SurrealDB has become our default engineering posture.
VP of Engineering, Later
GET STARTED
