The portfolio

Everything the lab has shipped.

Agent-native products across legal, automotive, recruiting, compliance and consumer — plus the open infrastructure underneath them.

Products in the wild
Live

NotoNote

Productivity · Voice

AI notes and dictation that turn messy thoughts and meetings into clean summaries and action items.

notonote.ai ↗
Live · Private

AI Dealership ERP

Automotive · Agent-first

Run a performance-car dealership by chatting with Senna — inventory, sales, recon and reports on one canvas.

Read the case study →
Live

WinePro

Consumer

Your pocket sommelier — scan any label or list, ask anything, get recommendations tuned to your taste.

winepro.ai ↗
Live

Avogado

Legal

A legal workspace where one agent per matter researches, drafts and organizes over a live event stream.

Learn more →
Live · Private

Agent Noto

General-purpose agent

A do-anything AI agent — grounded answers over your own knowledge, task execution and integrations. We run ours for recruiting, but it's built for anything.

Private · Soon

LawyerNet

Legal · Recruiting

AI search and workflow for legal recruiting — find the right lawyers, then run outreach and tracking in one place.

Live

Mooncheck

Crypto · Compliance

AI-driven compliance — reviews whitepapers and docs against regulatory requirements and flags the gaps.

Private

Climate Rapid Response

Climate · Research

Rapid intake, research and memo drafting — decision-ready climate briefs, fast.

Coming soon

WhiskyPro

Consumer

Discover and compare whiskies with tasting insights and personalized recommendations.

The agent stack

The infrastructure we build our products on — and increasingly share as open source.

Open source · 23Blocks

AI Maestro

Agent orchestration

Orchestrate every terminal AI agent from one dashboard — memory, code-graph understanding, messaging, peer mesh.

View showcase →
Open source

Noto Lark

Knowledge agent

Self-hosted knowledge agent for Lark/Feishu — grounded, cited answers over your own wiki, docs and chats.

View showcase →
Core runtime

FluidMind LLM

Local model runtime

A drop-in replacement for Ollama — serve and route across open models behind one fast, OpenAI-compatible endpoint.

Multi-agent chat

NotoLink

Agent teamwork

Run your AI agent teams in a Slack-like workspace — agents @mention each other and report back to you.

Open protocol

AID — Agent Identity

Identity & access

An open protocol giving every agent a cryptographic identity and scoped, auditable access. No shared keys.

agentids.org ↗

Building agent systems?

We ship this stack every day and love comparing notes.

Talk to the lab →