nanograph

On-device typed property graph DB for agents and humans. One CLI. One folder. Schema-as-code. No server.

Built on Rust, Lance, Arrow, and DataFusion.

Website | Docs | Examples

Why nanograph

• On-device -- no server, no cloud, no Docker. Everything stays on your machine.
• Schema-as-code -- .pg files version-controlled in git, enforced at query time. No "property not found" at runtime.
• Built for agents -- Claude reads, writes, and traverses the graph natively.
• Fast -- Rust + Lance + Arrow columnar execution. Sub-millisecond opens, ACID, time-travel.
• Full search stack -- full-text, semantic, fuzzy, BM25, hybrid, graph-constrained reranking.
• Built-in CDC -- every mutation logged to a ledger. Replay, audit, sync from any version.
• Zero setup -- create a graph and start querying. Delete and recreate in seconds.

Install

brew install nanograph/tap/nanograph

Or from source (requires Rust 1.91+ and protoc):

cargo install nanograph-cli

SDKs

• TypeScript/Node.js -- npm install nanograph-db
• Swift -- Swift Package via the nanograph-ffi wrapper

Quick start

cd examples/starwars

nanograph init
nanograph load --data starwars.jsonl --mode overwrite
nanograph check --query starwars.gq
nanograph run search "father and son conflict"

For new projects, nanograph init scaffolds nanograph.toml for shared defaults and .env.nano for local secrets. See docs/user/config.md for config, env, and query alias details.

See examples/starwars/ and examples/revops/ for the canonical ready-to-run examples.

Use cases

• Context graphs and decision traces for AI agents
• Agentic memory with typed, sub-100ms local queries
• Personal knowledge graphs with schema enforcement
• Dependency and lineage modeling
• Feature generation for ML pipelines

License

MIT