Why CognoDB
The differences, stated without hand-waving.
No unsourced multiples, no “fastest” anything. Four concrete differences, each verifiable — and a footnote for every number.
- 1Read-only throughput — 40 concurrent clients replaying a seeded workload for 60 s. The mixed run (10% writes) sustained 62,189/s. July 2026 graph benchmark: SNAP soc-Pokec (1.63 M nodes, up to 30.6 M edges) on one n2-standard-8 (8 vCPU / 32 GiB), CognoDB on defaults, median of 3 reps after warm-up.
- 2p95 latency for a two-hop, friends-of-friends traversal against the loaded graph. July 2026 graph benchmark: SNAP soc-Pokec (1.63 M nodes, up to 30.6 M edges) on one n2-standard-8 (8 vCPU / 32 GiB), CognoDB on defaults, median of 3 reps after warm-up.
- 3Edges merged per second over a fixed 60 s window (CognoDB wrote 2.70 M edges in its minute). July 2026 graph benchmark: SNAP soc-Pokec (1.63 M nodes, up to 30.6 M edges) on one n2-standard-8 (8 vCPU / 32 GiB), CognoDB on defaults, median of 3 reps after warm-up.
- 4On-disk store size divided by edges loaded, read from the container's cgroup counters — a compact store keeps the working set cached. July 2026 graph benchmark: SNAP soc-Pokec (1.63 M nodes, up to 30.6 M edges) on one n2-standard-8 (8 vCPU / 32 GiB), CognoDB on defaults, median of 3 reps after warm-up.
Fast reads, low latency, compact store.
Your drivers already work.
The price is the infrastructure cost.
Published rates, itemized to the line, billed by the second: $26.04 per vCPU-month, $3.49 per GB of memory, $0.113 per GiB of storage. There is no list price with a discount behind a sales call — the estimate on the pricing page is generated by the same cost model the billing engine charges from.
A paused instance costs only its storage. A quiet tenant is close to free.
Billed by the second. A paused instance is charged for storage only.
Isolation as the default posture.
Every instance is a real database: its own credentials, its own storage, its own resource limits, reachable only through its own encrypted endpoint. Console identity and data-path credentials are deliberately separate layers, every administrative change is audit-logged, and backups restore to a new instance so recovery can't destroy evidence.
When a security review asks how tenants are separated, “each has their own database” is a complete sentence.
The data model
Why a graph at all.
The honest comparison isn't against another vendor — it's against the relational model these workloads usually start in.
| What an agent needs | Similarity search | Rows & joins | Context graph |
|---|---|---|---|
| Find what's connected, not just similar | Cosine distance only — no concept of an edge | A join per relationship type | Typed edges are the data model |
| “What depends on X?” at unknown depth | No traversal at all | Recursive CTEs, tuned per query | [*1..n] — depth is a parameter |
| Provenance on every fact | Metadata blob, invisible to search | Another audit table to maintain | An edge property — returned with the path |
| A private graph per agent or tenant | Namespaces in a shared index | A schema per tenant, migrations forever | An instance each — a credential boundary |
| Explain why this answer | A score, unexplained | Reconstruct the join path by hand | The path IS the answer — return it |
What we won't claim
The absences are deliberate.
No compliance badges we haven't earned, no SLA we haven't published, no benchmark wins over named competitors, no customer logos beyond the one customer who's really in production. When those change, this site will say so — plainly.
Start now
~98.7%
token efficiency at 2,000 entities — see the footnotes above
Judge it against your own workload.
The free tier exists so the evaluation is yours, not ours.
First-graph path
LiveCreate a free instance
No card. Ready in about a minute.
Connect your driver
bolt+ssc:// URI into the driver you already use.
Write two MERGEs
That's the entire shape of agent memory.
Point an agent at it
One MCP config block. No integration code.