Local-first · now in early access

Instant answers about your code — that never leave your machine.

Kenning turns all your repositories into fast, always-accurate, searchable knowledge — for you, your team, and your AI. Everything runs locally. Nothing is ever uploaded.

No cloudRuns offlineNo telemetry
kenning · your workspace Ready Up to date
98%
answers backed directly by your own code
RepositoryFilesCoverage
frontend1,204
backend2,010
shared860

Everything stays private.

Runs entirely on your own machine. Your code is never uploaded, shared, or sent anywhere.

Answers in an instant.

Ask about any part of your codebase and get a precise answer in milliseconds — not minutes.

Always accurate.

Every answer is backed by your real code and re-checked as you work — so you can trust what you read.

Fits your workflow.

Use it from your terminal, your browser, a native app, or right inside your AI assistant.

01 Explore

See how everything connects.

Search anything across every repository, jump straight to what matters, and watch a live map of your whole project come together — always current as you build.

  • Find anything across every repo, instantly
  • See how your code connects, visually
  • Stays up to date automatically as you work
02 Built for speed

Optimised to feel instant.

We obsess over speed and footprint so the tool disappears and you stay in flow — no waiting, no heavy setup.

Seconds

To understand a large workspace

Point Kenning at your repositories and it's ready in seconds, not minutes.

< 2s

To pick up your changes

Edits are reflected almost immediately, so answers always match what's on disk.

One app

Lightweight, no clutter

A single fast application — nothing to provision, nothing running in the cloud.

03 One workspace

Everything you need, in one place.

Search, understand, document, and monitor your whole codebase — without juggling a dozen tools.

Graph

See your whole codebase as a living, explorable map — and find how anything connects.

Memory

Capture the decisions and context behind your code, so your team can search them later.

Wiki

Always-current documentation for every repository, generated straight from your code.

Dashboard

Track index health and coverage across every repository at a glance, always up to date.

04 Native app

A full editor, built in.

Read, search, and edit your code in a fast native app — with an integrated terminal, command palette, and file tree. One window, everything on your machine.

  • Code editor with syntax highlighting
  • Integrated terminal & command palette
  • Jump to any file, symbol, or answer instantly
kenning — answer.rs
src/
answer.rs
index.rs
graph.rs
wiki.rs
// answers, backed by your code fn answer(q: &str) -> Reply { let hits = index.search(q); let r = verify(hits, "local"); r.reply() }
For AI agents MCP-native

Your AI assistant, without the re-reading.

Every fresh AI session normally starts from zero — re-opening files it already understood last time. Kenning gives your assistant a standing index to query instead, so its tokens go to your problem, not to rediscovering your codebase.

Ask

One question, one ranked answer — drawn from code, docs, and memory together.

Explore

Callers, callees, and blast radius for any symbol — without opening a single file.

Search code

Structured code search across every repository, returned as precise matches.

Recall

Past decisions and context, remembered across sessions — explained exactly once.

3 ways in

MCP · HTTP/SSE · CLI

Plug it into your AI assistant over MCP, script it over HTTP, or use it straight from the terminal.

17+

Languages understood

Rust, Go, Python, TypeScript, Java, C/C++, C#, Ruby, Kotlin, Swift, PHP and more — parsed into one graph.

~21s

To index a 30-repo workspace

11,400 files, cold. Re-checking the whole workspace when nothing changed takes under two seconds.

Get started

Request early access.

Early access is rolling out now. Leave your details and we'll reach out with an invite.


Prefer email? Send us a note. We never share your details.