Kroonen AI / Product studio

A small studio building useful AI people can own.

We create and operate the Libre Stack — open tools, hosted software, programmable communications, and original model research, all built without lock-in.

Explore the portfolio Work with the studio

Portfolio / 01—05

Products in the studio

One shared point of view, expressed across agents, interfaces, communications, and model research.

01 / Flagship agentEarly release

Libre Claw

A permissioned AI teammate for your terminal — local, hosted, or on Telegram.

Streaming model providers, local inference, coding tools, SQLite memory, and sandbox hardening in one terminal-native agent harness.

Permissioned local tools
OpenAI, Anthropic + Ollama
Persistent local memory
Telegram daemon mode

Visit Libre Claw View source

libre-claw / workspace

runtime / ollama/qwen3.5

› Review the failing build and prepare a safe fix.

01 / Read project context

02 / Found type mismatch in provider adapter

03 / Patch prepared · permission required

Allow write to src/providers/openai.py? [y/N]

Local-firstPermissionedMulti-provider

Answers, embedded

02 / Hosted productAvailable

Libre Bot

Documentation answers on your site, live in minutes — with your voice, your sources, and no data lock-in.

A free tier makes it easy to start; paid plans help fund the open Libre Stack.

SaaS

Try it free

03 / CommunicationsEarly access

Libre Phone

Calls, texts, voicemail, contacts, and IVR without paying a SaaS tax for a programmable number.

Twilio and Cloudflare turn a $1 number into a complete, lightweight phone desk.

Cloud app

Open the demo

04 / Open sourceActive

Libre WebUI

A quiet, private interface for local language models. No telemetry, no tracking, no cloud dependency.

A fast, keyboard-friendly workspace for Ollama and local-first AI workflows.

Apache 2.0

Product details Visit Libre WebUI

05 / Research programPlayground

Genesis 1B

A one-billion-parameter language model trained from scratch on two consumer GPUs.

Custom tokenizer, 60B-token multilingual dataset, and distributed training over PCIe.

Open research

Open playground

How we incubate

One studio, one bar.

Useful before impressive

Every product begins with a real constraint, not a trend forecast.

Ownable by default

Local-first options, portable data, and open tooling wherever they make sense.

Research feeds product

What we learn training models becomes better infrastructure, interfaces, and agents.

Design partners / collaborators

Have a hard problem that belongs in this portfolio?

We work with a small number of teams on local AI, agent infrastructure, model training, and product experiments.

Request a fit check See studio capabilities