KIRA
v0.1 · in developmentMITNode ≥ 203 dependencies

Your help center goes stale the day you ship. KIRA reads your code instead.

KIRA turns a codebase into a maintained knowledge base about your product, then answers your users' questions from it — in their language, grounded in what the code does, and never invented.

$ npm install -g askkiraQuickstartGitHub
Inputsrc/app/domains/page.tsx
// the router, the guards, the copy,
// the disabled states, the errors —
// whatever the product actually is
kira extract
Output.knowledge/domains/no-transfer.md
type: boundary
route: /project/:id/domains
confidence: high

Domain registration stays with your current registrar — there is no way to transfer it here.

One fact per file, committed to your repository. Reviewed in a pull request before a customer ever reads it.

The wedge

Docs drift. Code can't.

Every in-product help assistant on the market is grounded in documentation — articles, tickets, marketing pages. All of it describes the product as it was the last time somebody wrote it down. Source code cannot describe a product it does not build.

route

It knows where things are

Routes come out of your router, so a fact carries the path it lives at. The assistant hands the reader a working link instead of describing where to click — and it knows the same question means different things on different screens.

requires

It knows who can see them

When the code gates something behind a plan or a role, the fact carries that gate. Telling a Free user how to use a Business feature is worse than silence, and no help-centre article has a field for this.

boundary

It knows what you can't do

Code is full of guards, plan checks and unsupported branches. The costliest wrong answer here is not an invented feature — it is a confident yes to something the product refuses. So refusals are a first-class fact type.

git

It leaves a paper trail

Every fact records the files it came from, the commit, and the model that wrote it. Knowledge lives in your repo, so what you now tell users is a git diff — and nothing reaches a customer without review.

Recorded, not simulated

Ask it something

Real output from a real run: a two-fact knowledge base about custom domains, and the answers KIRA gave. The questions are in Russian against an English knowledge base, because that is where the interesting part is — retrieval matches words, so crossing languages is the thing that has to work.

KIRA · knowledge base: domains · 2 factsrecorded session
как подключить домен, который я уже купил?

Откройте Project settings → Domains и выберите Add existing domain.

  1. Введите имя домена.
  2. Скопируйте две показанные DNS-записи и добавьте их у своего регистратора.
  3. Проверка обычно занимает до часа — после неё домен получит статус Active.

Обратите внимание: перенести саму регистрацию домена сюда нельзя — она остаётся у вашего текущего регистратора, домен только указывается на проект.

Retrieved facts
domains/connect-existing1.63
domains/no-transfer0.49
Retrieval detail
asked in
Russian
searched for
connect existing custom domain
rewritten
yes

The answer is written from the reader's own words, so it comes back in their language — while interface labels stay verbatim in English, because that is what they have to find on screen.

Pipeline

How it works

Four stages. Each is independently useful, and each has its own command.

kira init

Propose the map

Scans the repo and proposes an area per user-facing page and per behaviour module, deriving routes from the router. You edit it: an area is a topic, not a directory.

kira extract

Read the code

Reads each area and writes what it means for the people who use the product. Incremental — an area whose sources have not changed is skipped entirely.

kira ask

Answer from facts

Retrieves, filters by who is asking and where they are, and answers from those facts only — with an honest “I don't have that” when they don't cover it.

kira eval · v0.2

Prove it

Generates questions per area, answers them through the real pipeline, judges the answers, and turns the weak ones into a documentation backlog.

Measured on a private production codebase

Two areas, four source files, extraction at high effort. Numbers only — the knowledge itself belongs to the codebase's owner.

35facts written
3m22swall clock
35/35carried a route
33/35high confidence