Genesis 1B
A 1B-parameter multilingual language model pretrained from scratch on two RTX 4090s, with a custom tokenizer and data pipeline.
- 1B parameters
- 80,004 steps
- ≈42B tokens processed
- 2 × RTX 4090
The Libre ecosystem · Five active builds
Small stack.
Full control.
Independent tools for teams that want to own more of their AI and communications infrastructure.
Each project explores a different part of the same question: how much of the stack can a small team run for itself?
01Research→02Open tools→03Operated products
How the studio compounds
The Libre stack
Research feeds open tools. Those tools sharpen the products Robin operates. Every layer creates evidence for the next.
Research
Train models, publish the failures, and turn the evidence into better products.
Open tools
Local-first interfaces and agents people can inspect and run themselves.
Libre WebUI
A self-hosted creative AI workspace for Ollama and cloud models, with plugins, RAG, artifacts, SSO, and a desktop app.
- Ollama + 10+ providers
- RAG, artifacts + plugins
- Apache 2.0
Libre Claw
A terminal-native coding-agent harness with durable runs, persistent memory, provider routing, browser tools, and a Telegram bridge.
- Textual TUI
- Durable runs + memory
- Multi-provider routing
Operated products
Focused hosted and cloud software for teams that want to start quickly.
Libre Phone
A lightweight phone desk on Cloudflare Workers and Twilio, covering calls, messaging, voicemail, IVR, and browser calling.
- Calls + SMS/MMS
- Voicemail + IVR
- ≈$1 number + usage
Libre Bot
An embeddable AI assistant for documentation sites, designed to add useful product-aware chat in a few minutes.
- Drop-in widget
- Sources + citations
- Five-minute setup
Working materials
The tools behind the tools.
- 01Python
- 02TypeScript
- 03React
- 04Node.js
- 05Cloudflare Workers
- 06PyTorch
- 07Twilio
- 08Docker
- 09SQLite