Install Sonn
Memory & reasoning for AI coding agents

The memory that actually thinks

Install Sonn
built for claude code · more agents coming · local-first

Sonn remembers every decision, stops your agent repeating mistakes you've already fixed, and learns how you code. Built for Claude Code — and your code never leaves your machine.

01 — The problem it solves

It catches the mistake
before your agent
makes it again.

A persistent process reasons over your history and steers before you ask — so settled decisions stay settled, instead of being relitigated every session.

session/cache.ts — claude code Sonn active
1$claude "add caching to the session store"
2
3-reach for an in-memory TTL cache
4-→ stale sessions across pods (again)
5
6+recall: we settled this in MaySonn reasoned, before you asked
7+use Redis with explicit invalidation
8+the approach the team already agreed on
02 — Why it's different

Not another
memory tool.

Persistent memory is table stakes — everyone has it. The whole category just stores text and hands it back. Sonn is the layer above that: it reasons.

Other memory tools
store embed search return

They compete on storage shape — vectors vs. graphs vs. paging. The memory itself never forms an opinion. They make the agent know more.

A filing cabinet.
Sonn
observe reason validate steer first

A persistent process reasons over the memory — forms opinions about what matters and injects guidance before you ask. It makes the agent behave better.

A mentor.
03 — How it works

Three layers over
one local database.

One SQLite database on your machine, doubling as the vector store. The bottom layer is the commodity everyone ships. The two on top are the product.

03
WhisperBehavior

Your rules become trigger-gated nudges that fire the moment they're relevant — changing how the model behaves, not just what it knows. The closest thing to fine-tuning a model without its weights.

02
AngelReasoning

A persistent process that reasons over the memory — forms opinions, extracts patterns, and surfaces the right context before you ask. When it isn't confident, it says so and re-queries instead of returning noise.

01
MemoryStorage

Records every session, embeds it, retrieves it with hybrid search. The part every other tool stops at.

// layer 01 is a commodity. layers 02 + 03 are Sonn.
04 — Your code stays yours

Nothing of yours
runs on our servers.

Sonn is local-first. Your memory database lives on your machine, and generation runs through your own model credentials — your source goes to the provider you already trust, never to a third-party server. We hold the reasoning logic. You hold the code.

your code→ your machine
memory db→ your machine
generation→ your own credentials
reasoning logic→ Sonn (our IP)
0bytes of your source on our servers
05 — The numbers that matter
0.0%
LongMemEval — on a local model
426 / 470 · competitive with the best published results
0
lines of your code on our servers
local-first · your own trust boundary
Get started

Give your agent
a memory that thinks.

If you're reading this, you're early — and that means a lot to us. We're developers shipping the tool we always wanted. Try it, break it, tell us everything.

Install Sonn
built for claude code · local-first · early access