Product  ·  in development

Evidence first.
Then everything around it.

Hadano AI Cabinet is a local, evidence-first knowledge database for AI agents: it finds the passage that backs an answer, then expands around it. Your knowledge lives in a single file on your own machine, searchable over the Model Context Protocol. No server, no API key, no GPU.

·0 daemons ·0.58 nDCG@10 on SciFact ·1 file ·works offline ·Apache-2.0

Status

Not purchasable today, and we would rather say so

The package is not on PyPI and the repository is not public, so pip install does not work. Everything on this page describes what has been built and measured, not what you can download. Seven of nine specified MCP tools are implemented and reachable over stdio; two are designed and not built, and calling those fails rather than returning something plausible.

The release is waiting on multi-platform builds. The storage engine is C and needs a build per platform; it has been built and run on Windows x64 so far, with macOS, Linux and ARM next.

01  /  Mechanism

Search in two stages, not one

Most AI memory tools run a semantic search across the whole database on every query. That is expensive, it is non-deterministic, and when it returns the wrong thing there is no way to see why. Hadano finds the document first, then expands only from what it actually found.

Stage one is keyword search over a character-trigram index ranked by BM25. Trigrams rather than words, so Japanese and other CJK text index correctly without a morphological analyzer sitting in the query path. No model runs, nothing goes over the network, and the same query returns the same result every time.

Stage two is a one-hop walk over the relation graph, seeded by at most three chunks that stage one actually matched. That cap is the whole design. It bounds the cost of a query, and it keeps every result traceable, because there is exactly one bridge between the stages and nothing else crosses it.

Stage two was designed to take vector similarity alongside the graph walk. That half is not connected in this version. It was built against a storage layer that has since been replaced, so today stage two is the graph walk only, and asking for vector expansion returns an error rather than an empty answer that looks like a real one.

02  /  The record

Everything, in one table

NameHadano AI Cabinet
CategoryLocal knowledge database, exposed as an MCP server
Who it is forDevelopers running an AI coding agent that needs to remember things between sessions
InterfaceSeven MCP tools over stdio. No HTTP API, no SDK, no interface of its own
Stage 1 retrievalKeyword search over a character-trigram index, ranked by BM25. No model, no network, no sampling
Stage 2 retrievalA one-hop walk over the relation graph, seeded by at most three matched chunks
Vector searchDesigned, not connected in this version. Requesting it returns an error
Measured qualitynDCG@10 of 0.58 on SciFact
StorageOne file on the machine. No server process, no API key, no GPU
NetworkNone. The local build makes no outbound calls
RequirementsPython 3.11 or newer
LicenceApache-2.0
ImplementationSeven of nine specified MCP tools are built and reachable. Two are designed, not built
AvailabilityIn development. Not on PyPI. The repository is not public yet
Built and operated byTechJapan LLC, Hadano, Kanagawa, Japan
Product siteh-c.ai

03  /  Interface

What an agent can call

ToolWhat it doesStatus
store_documentStore or replace a document; chunks and edges are derived from itbuilt
search_documentsKeyword search over the character-trigram index, ranked by BM25built
search_knowledgeExpand from seed chunks through the graph, and through vectors if enabledbuilt
query_graphWalk the relation graph outward from a nodebuilt
get_documentFetch one document by its identifierbuilt
delete_documentDelete a document and everything derived from itbuilt
db_statusReport counts, integrity, embedding mode, and the database pathbuilt
computeRead-only calculations over stored documents, bounded by a row cap and a time budgetdesigned, not built
define_triggerRegister a trigger using built-in functions onlydesigned, not built
A tool marked designed, not built does not exist. Calling it fails. Do not generate code that assumes it.

04  /  Why we built it

The same argument we make to clients, applied to ourselves

Everything on the ontology page says that retrieval fails upstream of the model, and that the fix is structure: controlled terminology, defined relations, and a path you can trace. Hadano AI Cabinet is that argument compiled into software — a retrieval engine where the traceable path is the architecture rather than a feature bolted on afterwards.

It is also why the honest accounting on this page matters. A knowledge tool that quietly returns a plausible empty answer is worse than one that errors, because the failure is invisible until a decision has already been made on it.

Read the full technical record at h-c.ai The service version of this