Vector DBs are recall — that's a search engine, not a brain. A brain has structure, time, and the ability to answer: what did I know when I decided that? That's a temporal graph. That's Graphiquity.
“Your agent made the wrong call yesterday. Can you replay exactly what it knew at 3:47pm when it decided?
Vector DBs say no. Graphiquity says AT RECORDED '2026-04-13T15:47:00Z'.”
Built into the database itself — not bolted on as a layer above embeddings.
Outlives context windows, process restarts, and multi-instance scaling. State lives in the graph, not in the agent process.
Real graph structure: entities, facts, sessions, contradictions. Query with Cypher. Not just “k-nearest neighbor on a blob.”
Bitemporal by default. Replay agent memory state at any past moment with AT RECORDED. The bitemporal moat: no other memory store can do this natively.
Tamper-evident hash chain over every memory mutation. Stamped _actor=agent:<id>. WORM mode optional. The audit trail comes for free.
Multi-agent collaboration through cross-graph queries. One agent's findings inform another's. Federated by design, isolated by default.
Agent memory can be projected into structured JSON documents. Define a template once, and episodic graph memory materializes into documents with full bitemporal replay.
npm install @graphiquity/memory — then record, recall, and time-travel.
Zep, Mem0, Redis-vector, pgvector. They're search engines. We're a brain.
| Capability | Graphiquity | Vector memory stores |
|---|---|---|
| Persistent recall across sessions | ✓ Yes | ✓ Yes |
| Structured entities & relationships | ✓ Native graph | × Embeddings only |
| Multi-hop reasoning over memory | ✓ Cypher MATCH | × No traversal |
| Time travel (replay memory at a past moment) | ✓ AT RECORDED |
× No bitemporal |
| Tamper-evident audit trail | ✓ Hash chain | × None |
| Per-agent isolation (auth model) | ✓ One graph + scoped key | × Namespace at best |
| Multi-agent collaboration | ✓ Cross-graph query | × Manual sync |
| Reversible auto-corrections | ✓ Append-only versioning | × Mutate in place |
We dogfood the SDK. These are real agents shipping in the platform.
Nightly agent that audits a graph's schema, indexes, and query patterns. Suggests reversible improvements with cost/benefit math.
Auto-approve agent. Watches the Advisor's suggestions, applies the reversible ones automatically per your policy.
always / staging-only / notify / noneInteractive agent for fraud, breach, and claims investigation. Read-only by protocol, with full case memory accumulating across sessions.
query, explain, describe_graph, sample_data, recall_prior_cases, save_finding, propose_write, concludeOne graph per agent. Scoped API keys. Short TTLs. Hash-chained audit. The blast radius of a compromised agent is one memory graph.
Each agent instance gets its own memory graph. Cross-agent reads require explicit key scope.
Keys carry auth.graphs, auth.tenantId, apiKeyRole. Engine enforces at every call.
Independent query/mutate buckets per key. Runaway loops hit 429 with Retry-After.
Default 7 days for agent keys. Rotated by orchestrator. Leaked keys expire.
Every mutation stamped _actor=agent:<id>. Filter the access log by actor for replay.
Auto-apply endpoints accept only reversible operations. Append-only history covers the rest.
Free to start. Ship in an afternoon. Replay forever.