Question 1

How do I get started with Spectron?

Accepted Answer

Join the waitlist for early access - it doubles as the design-partner application. Once you have access, you create a Spectron Context on SurrealDB Cloud and connect: from an MCP client (Cursor, Claude Desktop, Claude Code) it is a single configuration entry; from application code, install the TypeScript SDK (@surrealdb/spectron); from the terminal, install the Spectron CLI with one command. Harness adapters for LangChain, OpenAI Agents, Vercel AI SDK, and n8n flush conversations into the substrate automatically, and Zapier connects via MCP. Self-serve plans open at launch, each starting with a one-week free trial.

Question 2

How is Spectron different from Mem0, Zep, or Letta?

Accepted Answer

Memory middleware libraries orchestrate two or more separate stores - typically a vector database, a graph database, and a row store - and absorb the consistency gaps in application code. Spectron is the database: graph, vector, document and structured records commit in one ACID transaction. Authoritative knowledge (uploaded documents) and experiential memory (conversational input) flow through the same reconciler into a single entity and relation graph, distinguished by provenance rather than by a separate store. Multi-tenancy, supersession, tri-temporal history, and trace-graph audit are engine-enforced, not application code.

Question 3

How is Spectron different from a vector database like Pinecone or Weaviate?

Accepted Answer

Spectron is not a vector database. Vectors are one signal among eight in the fused ranker - alongside BM25, graph traversal, keyword bridges, document links, PageRank, geographic recall, and trace-derived features. Embeddings-only retrieval has known failure modes (near-duplicates dominate top-k, rare-term queries miss the right chunk, structure between facts is invisible). Spectron's structural index is built at write time and read cheaply on every retrieval, with per-feature scores recorded on every trace - so retrieval is auditable, not black-box top-k.

Question 4

How is Spectron different from specialist agent databases?

Accepted Answer

Specialist agent databases saw, correctly, that flat vector stores fail for agent memory. But they respond by internalising a multi-store architecture instead of eliminating it: a vector index, a graph store, and a row store coordinated inside one product, with the seams moved rather than removed. Spectron is one engine - graph, vector, document and structured records commit in one ACID transaction, under one permission model, with provenance and tri-temporal history on every fact.

Question 5

Why not just use Postgres with pgvector?

Accepted Answer

pgvector adds vector similarity to Postgres, but agent memory needs more than similarity. There is no native graph to traverse, no tri-temporal versioning to answer 'what did we believe on date X', and no unified transaction across data models - so the glue code between extensions and sidecar stores becomes the product you maintain. Spectron is built on SurrealDB, where graph, vector, document and structured records are one engine and one transaction, with supersession, provenance, and audit built in.

Question 6

Does Spectron replace my agent runtime or manage the context window?

Accepted Answer

No. Spectron is the durable memory and knowledge layer behind an agent, not the in-prompt scratchpad and not the orchestration loop. The agent decides what to put in the context window; Spectron decides what to remember. POST /chat is a convenience composition over /facts and /query for callers who want Spectron to be an agent, but model orchestration, tool calling, and planning loops stay with your runtime of choice - including LangChain, OpenAI Agents, Vercel AI SDK, and n8n; MCP clients such as Claude Code connect directly.

Question 7

How does Spectron prove that an answer is grounded in the substrate?

Accepted Answer

Every fact-bearing row carries a source object: kind, ref, trust, lexical span (byte offsets into the originating turn or document), location, and derived_from. Every read produces a retrieval_trace listing the candidates considered and the rows returned; every decision produces a decision_trace recording created, superseded, and flagged rows; every response produces a response_trace linked to the retrievals and decisions behind it. Together they form a graph-resident audit log - any answer can be walked back to the retrievals it used, the entities those retrievals returned, and the bytes those entities cited.

Question 8

Is Spectron open source?

Accepted Answer

SurrealDB, the database engine underneath, is open source and free to self-host. The Spectron memory layer on top is closed source and ships as a single Rust binary with no Python runtime and no sidecars. Our roadmap intent is to upstream foundational parts of the Spectron memory model into SurrealDB over time so the most fundamental primitives remain open.

Question 9

How much does Spectron cost?

Accepted Answer

Spectron pricing will be published when self-serve access opens. Join the waitlist for early access, or talk to sales about enterprise packages and design-partner engagements. SurrealDB, the database engine underneath, is open source and free to self-host.

Question 10

Where does my data go, and can I delete it on request?

Accepted Answer

Spectron runs on SurrealDB Cloud today, with enterprise deployments running single-tenant. Tenant isolation is at the substrate level: each Context is its own SurrealDB namespace and database, and cross-Context reads are not expressible in the API. The four LLM hooks (extraction, reconciliation, synthesis, background) are configurable per Context, including any OpenAI-compatible, Anthropic, Google, or local provider. The embedding model is fixed to Google gemini-embedding-2 at launch, so embedding calls Google's API; per-Context embedding selection is on the roadmap. Self-hosted and air-gapped deployments, with local model inference, are available for qualifying enterprise engagements. forget is a first-class verb, distinct from natural aging: it removes derived rows (entities, attributes, relations, and any traces touching the target), the originating turn or document if requested, and the object-store original by content hash. Supersession history is retained by default for audit; a --purge flag removes that too.

Agent memory
you can trust

Agents fail because of context, not models.

Anatomy of an agentic system

Every turn: read → think → write

READ

THINK

WRITE

Typed memory, not a blob.

Episodic

Identity

Knowledge

Context

Instructions

Uncertainty

And it's all connected in a knowledge graph

Recall that surfaces the right thing.

One engine, not a pile of stores.

The architecture, row by row

Drop it in beneath your agent.

It changes its mind without losing the past.

Connects to everything you already use

Give your agents a memory that lasts

Spectron FAQ

Agent memory.__m__-_R_1almn8mmn_{display:none;}@media(min-width: 62em){.__m__-_R_1almn8mmn_{display:block;}} you can trust