Request early access

Product Research Open source Company Request early access

Research

RFCs, design docs,
benchmarks.

Every architectural decision lives in an RFC. Every benchmark is published — including the ones that don't go our way. We work in the open because the engine you depend on should not be a black box. Twenty RFCs at the time of writing — seventeen shipped, three in active draft.

The principles

Decisions are written down. Argued in public. Reversed when wrong.
Benchmarks include the dataset, the scale, the hardware, and the raw runs.
The numbers that don't flatter us are published with the ones that do.

Open source Benchmarks

Storage

4 RFCs

How NamiDB lives on object storage — layout, format, read path, adjacency.

Storage engine on object storage.

LSM tree over S3 / GCS / R2 with manifest CAS as the coordination primitive. Conditional writes shipped by S3 in 2024 — the last missing piece.

SST format — columnar, Parquet-derived.

The on-disk layout of a NamiDB segment. Columnar property storage, sidecar bloom filters, footer metadata for row-group pruning.

Read path — ranged reads.

Why we serve cold reads with per-row-group GETs rather than full-body downloads. Closes a 14× gap against real-WAN R2 in measured benches.

CSR adjacency — shared across snapshots.

Compressed-Sparse-Row adjacency lists held cross-snapshot in RAM. The reason traversals run in microseconds.

Query

11 RFCs

Parsing, planning, optimisation, execution. The eleven RFCs that close the Fase 2 gate.

Cypher subset.

The slice of Cypher 25 that NamiDB parses and executes today. The grammar is the contract — what isn't in the subset fails fast.

Logical plan IR.

The intermediate representation every query lowers to. Optimizer passes and rewrite rules operate here.

Write clauses.

CREATE, MERGE, SET, DELETE — how mutating Cypher clauses lower to WriterSession operations against the LSM tree.

Cost-based optimizer.

Cardinality estimation, join ordering, and cost-driven plan selection. The reason IC02 runs in microseconds.

Predicate pushdown.

Push WHERE clauses down to scan operators. Skip row groups whose statistics rule them out. Decode only what survives.

Hash join.

The default join strategy. Build side, probe side, spill discipline.

Parquet predicate pushdown.

Push predicates through the Parquet reader so row groups never decode. Saves the I/O — and the cycles.

Hash semi-join.

EXISTS / IN as a cardinality-preserving semi-join — not a join + distinct.

Projection pushdown.

Only the columns the query needs make it past the scan. Columnar storage's natural advantage.

Join reorder.

Dynamic-programming join enumeration. The optimizer picks the cheapest order, not the textual one.

Factorization.

Factorized intermediate results — avoid materialising the full Cartesian product. Behind the IC09 win.

Caches

2 RFCs

Cross-snapshot caches that make warm reads cost the price of a hash lookup.

Node view cache — cross-snapshot.

Lookup cache for NodeView reads that survives snapshot boundaries. The second read of the same node hits, even from a newer snapshot.

Edge SST caches.

SST bodies, decoded edge property streams, parsed EdgeSstReaders. The fastest read is the one that never crosses the storage boundary.

Next

3 RFCs

Drafts in active design. Each lands before the feature does.

Hybrid retrieval — vectors and graph.

Why we co-locate the vector index with the graph rather than federating two stores. Trade-offs on recall, latency, and operational cost.

Text-to-Cypher — schema-aware, cost-aware.

A natural-language layer that validates against the live schema and rejects queries that would over-fetch. The grammar is the contract.

GQL surface — ISO 39075 in a column store.

How we map the ratified GQL standard onto a columnar execution engine. The bits where the spec leaves implementation up to the vendor — and how we chose.

Full archive at docs.namidb.com/rfc. Contributions via the open GitHub repository.

Build the next decade with us.

Early-access is open. One launch email when the engine is ready — never spam.

Request early access