The cognitive OS for AI.
#1 on LongMemEval.500/500.Beats Mem0, Zep, and the federated stack — on one engine.
Memory, vector, graph, and analytics — one engine, one API, no glue code.
The numbers, against everyone else.
Public, third-party benchmarks lead. The head-to-head infrastructure comparison follows. Every caveat stays visible — that's why the wins are believable.
#1 on the public leaderboard
Competitor figures are published raw scores on the same dataset where available. Judge model and scoring convention vary by system; several report task-weighted averages above their raw counts. We show the full field — leading it is the point.
Recall vs Mem0 — hit_any %
BEAM top-200 hit_any (%), single-pass retrieval. At 10M tokens, where other systems collapse, Akasha holds 84%. Mem0 figures are its published numbers.
Tokens / query vs Mem0 — lower is better
Mean tokens retrieved per query. 16–18% fewer than Mem0, every compact surface under 7,000 tokens — higher recall on a smaller context.
One engine beats the stack you'd assemble
Beats hnswlib on QPS and every latency percentile at matched recall (0.9989–0.9991).
Caveat — hnswlib builds its index faster — the win is serving, not build time.
Faster on all 21 LDBC queries vs Kuzu & Neo4j; 54–359× on bi-temporal vs a Neo4j app-layer.
Caveat — Bi-temporal margins are vs an application-layer baseline, not a native engine.
DataFusion-class speed with 44–48× lower fresh-write read latency.
Caveat — On raw ClickBench OLAP, Akasha is at parity — not faster.
Every figure is reproducible — CSVs, audit hashes, and the harness are public.
Reproduce it yourselfTeams assemble memory from four databases.
We replaced them with one.
KV + Vector + Graph + SQL. One async API, cross-modality joins, ANN inside SQL. No glue code, no sync lag, no four bills.
- One async API
- Cross-modality joins
- ANN inside SQL
- No glue code, no sync lag
- Read-your-writes 1.000
One substrate, five layers — KV up through cognition.
See the L0–L5 architectureSix stages. One loop. Endless improvement.
Perceive.
Raw experiences — queries, tool results, sensor reads — flow in. Deduplicated, scored for novelty, batched.
Read the specAttend.
The attention filter ranks signals by salience. Only what matters reaches consciousness via the Global Workspace.
Read the specDecompose.
Triples persist to the knowledge graph. Episodes flow into episodic memory with source attribution. Embeddings index in HNSW.
Read the specReason.
HRM hierarchical planning — H-module decomposes the goal, L-module executes. Neurosymbolic blends neural similarity with symbolic paths.
Read the specLearn.
Reward-modulated Hebbian updates strengthen pathways that worked. EWC protects critical weights. Unused connections decay.
Read the specAct.
The selected action emits. ActionFeedbackAdapter routes the result back into Perceive. The loop closes. The agent improves.
Read the specEvery memory an agent needs, in one place.
Most AI memory products give you one shape: a vector blob. Minds gives you the full neuroscience-grounded hierarchy — episodic, procedural, resource, vault, working, and associative — unified under one async API.
Agents remember what they did.
Every session captured with goal, outcome, valence, source. The StreamSparkline shows event importance over time. Auditable forgetting handles GDPR delete-requests cryptographically.
Plans like a strategist.
Grounded like a lawyer.
The Hierarchical Reasoning Module (HRM) plans abstractly, executes concretely, and decides when to stop. Neurosymbolic fusion grounds every embedding in a symbolic path — hallucinations become a hardware problem you can fix.
Know what was true, when it was true, and when you learned it.
Every node and edge tracks two timelines — valid time and transaction time. Time-travel any query. Causal-path discovery, counterfactual queries, microtheory scoping, Merkle provenance.
Process time the way brains do.
Nengo-inspired, Rust-native SNN engine. LIF, Izhikevich, STDP, BPTT. Ideal for tick streams, sensor data, and log anomaly detection.
Sub-millisecond search.
A brain in your binary.
One substrate. Six superpowers.
Time-travel any query.
Every fact tracks valid time and transaction time. Know what you believed when.
KV + Vector + Graph + SQL. No glue code.
One async API. Cross-modality joins. ANN inside SQL.
Train forever. Never forget.
EWC, SI, Generative Replay, and a learning quarantine that rejects poison.
AES-256-GCM. BLAKE3 audit chain. OIDC.
Multi-tenant from the kernel. Differential privacy guardrails. Air-gappable.
630K writes/sec. Sub-10ms vector.
LSM-tree with WAL group commit, lock-free buffer, TinyLFU cache.
Self-improves while you sleep.
The cognitive cycle rewards pathways that work. Hebbian + decay.
Every belief, traced to its source.
Knowledge lineage tracks how every fact was derived. Belief-taint tracking ensures untrusted sources cannot launder into Tier-1 recommendations. Auditable forgetting handles GDPR delete requests cryptographically.
The kernel underneath every memory.
Akasha is the cognitive database engine that makes Minds possible. An LSM-tree KV with WAL, MVCC, and lock-free buffers that hits 630K writes/sec — and the substrate every higher-level layer (memory, reasoning, learning) rides on.
Launch exactly the engine you need.
Toggle a capability on and watch the architecture, the provisioning command, and the price update live. Start with KV; add graph when you need it.
Every capability is free on the shared pool. No feature wall — graph included.
Start with KV. Add graph when you need it. No migration, no downtime, no re-provision — capabilities snap into a running instance.
Your data, isolated and encrypted, on a shared regional pool. Instant start, scale-to-zero economics. For prototyping and cost-sensitive workloads.
Your own isolated instance with predictable performance, resize on demand. Same encryption and isolation as shared — for production and scale.
Data isolation and encryption are identical on shared and dedicated.
Provision your engineOne call. Five languages. Same answer.
Native SDKs for TypeScript, Python, Rust, and Go — plus the cogs CLI and the mind TUI control room. All five wrap the same daemon API.
import { Minds } from "@minds-sdk/typescript";
const minds = new Minds({ apiKey: process.env.MINDS_KEY });
// Hybrid retrieval: vector + graph + episodic, one call.
const memories = await minds.recall({
query: "Why did Q3 revenue dip?",
modes: ["vector", "graph", "episodic"],
timepoint: "2026-10-01",
topK: 5,
});
for (const m of memories) {
console.log(m.confidence, m.source, m.text);
}Built for any system that needs to remember and reason.
Enterprise-ready the day you adopt it.
Multi-tenant from the kernel. Cryptographic provenance on every fact. OIDC + PKCE auth via Hydra. SOC 2 and ISO 27001 paths in flight.
Don'tfine-tunetheLLM.Traintheagent.
Domain-specific intelligence belongs in the substrate that persists, not the weights that get replaced every six months. Minds gives your agent a brain it carries forward — across sessions, across model upgrades, across the lifetime of your company.
Every capability, every tier.
No feature walls. Graph, vector, and analytics are the same substrate — so they're on from the free tier up. Start on a shared pool, grow into your own instance, compose exactly what you run.
- 50,000 memories / month
- Generous retrieval — no tight call cap
- 1 shared namespace · scale-to-zero
- No credit card · never expires
- Community support
- 1,000,000 memories / month
- Higher throughput, isolated & encrypted
- Hot-loading included
- Storage included
- Email support
- Your own isolated instance
- Modular — KV, Graph, Analytics, HRM, SNN
- Resize on demand · predictable performance
- Add capabilities with no migration
- Priority support
- Self-hosted, VPC, or air-gapped
- SOC 2 / ISO 27001 in flight
- Bi-temporal provenance · BLAKE3 audit chain
- Contractual data isolation (DPA)
- Custom SLA · 99.99%
- Dedicated solutions architect
We never train on private data. Aggregated performance metrics help us improve the engine — and if you ever want to contribute more, it's opt-in, always. How we treat your data