Solution · Research

Research that remembers, with provenance.

Episodic memory of every paper read. A semantic graph of every citation. HRM-planned literature reviews. Source monitoring distinguishes 'Paper X claims' from 'I inferred.' Counterfactual queries: 'what if N=500?'

Start free Read the docs

Capabilities

What you get.

Production-grade from day one. No flags, no betas — these ship when you adopt Minds.

Citation graph

Every reference becomes a graph edge with provenance.

Source monitoring

Observed · inferred · imagined · reported · reconstructed.

Counterfactuals

Ask 'what would change if X were different?' over the graph.

Literature planning

HRM decomposes a research question into ordered subgoals.

Domain continual learning

Skills compound across sessions, not just within one.

Audit-grade lineage

Defensible to a peer reviewer — every belief traced.

API

A few lines is all it takes.

exampletypescript

const result = await minds.research.run({
  question: "Does intermittent fasting improve insulin sensitivity?",
  priors: ["pubmed", "biorxiv"],
  microtheory: "endocrinology",
  budget: { papers: 40, hours: 2 },
});

console.log(result.summary);
console.log(result.lineage);  // every claim traced to its paper

Specs

What it costs, what it guarantees.

At a glance

Source attribution: 5 levels
Graph traversal · 5-hop: <100ms
Microtheory contexts: unlimited
Auditable: BLAKE3 Merkle chain

Guarantees

Durability: fsync per WAL commit
Isolation: MVCC · snapshot
Audit: BLAKE3 Merkle chain
Encryption: AES-256-GCM per-namespace
Concurrency: 100K+ ops/sec

Keep exploring

Knowledge Graph

Where citations live.

Reasoning

HRM-planned research.

Continual Learning

Skills compound.

Get started in an afternoon.

Run anywhere — Akasha Cloud, on-prem, or air-gapped.

Start free Talk to sales