An AI lab · Where AI flows

We build minds that flow

AI systems that think, adapt and deliver.

See what we're building → Meet the lab
Scroll ↓
The Lab

A tiny team.
An army of agents.

We're an AI lab where humans and agents work side by side. Product, creative and data-science expertise, amplified by intelligent systems that let us punch far above our weight.

User-first design AI-native workflows Small team, big output
0
Products shipped
0
Industries
0
Open protocols

The future of AI isn't smarter models.

It's better experiences.

What we do

The building blocks behind every product.

Autonomous agents

AI that acts on your behalf — researching, organizing and executing tasks with minimal oversight.

Intelligent workflows

Multi-step pipelines orchestrating LLMs, APIs and data sources into seamless automated processes.

Knowledge systems

Beyond basic RAG — graph structures, multi-hop reasoning and context-aware synthesis across complex data.

Document intelligence

Generate, analyze and transform documents at scale — from contracts to reports to any format you need.

Voice interfaces

Natural dictation and voice-driven workflows that capture intent the moment it happens.

Agent infrastructure

Identity, orchestration and messaging — the protocols and tooling that let agent systems actually ship.

Products in the wild

Shipped software, solving real problems in real industries.

NotoNote Available now

NotoNote

Never miss what matters.

AI notes and dictation that turn messy thoughts and meetings into clean, usable outputs — captured by voice, structured by agents into summaries and action items.

DictationAI summariesAction items
Visit notonote.ai →
NotoNote ● 02:14
Transcribing live…
✦ Summary
☑ Send Dana the deck☑ Book venue Friday
Avogado Live now

Avogado

One matter. One agent. One private space.

A legal workspace built as a thin, rich client over an agent's live event stream. Open a matter and work it end to end — the agent researches, drafts and organizes documents right alongside you.

Agent per matterLive event streamPrivate by design
Explore Avogado →
Avogado
Matters
Acme v. Hollis
NDA — Vela Labs
Series A — Orin
Acme v. Hollis
Summarize the deposition and flag risks.
◈ risk-memo.pdfdraft
Avogado is working···
Case study · built for Live · Private
Absolute Auto Club

AI Dealership ERP

Run the whole dealership by talking to Senna.

An agent-first ERP for Absolute Racing Japan. Staff operate inventory, sales, reservations, reconditioning and reports by chatting with Senna — which renders answers on a dark canvas and proposes writes you approve.

Agent-first UXInventory & salesApprove-to-write
Read the case study →
Absolute● SENNA
184
In stock
¥42.8M
MTD sales
7
In recon
GT-R Nismo '22¥18.4M
Supra RZ '21¥9.2M
911 GT3 '20¥21.0M
margin on the GT-R Nismo
WinePro Live

WinePro

Your pocket sommelier.

Scan any wine list or label, ask anything, and get smart recommendations tuned to your taste — a sommelier's intuition, in your pocket.

Label scanTasting notesRecommendations
Visit winepro.ai →
WinePro
WinePro app
◎ scanning label
And more across the portfolio

Agent Noto

Live · Private

A do-anything AI agent — grounded answers over your knowledge, task execution and integrations. We happen to run ours for recruiting; it works for anything.

LawyerNet

Private · Soon

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

Mooncheck

Live

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

Climate Rapid Response

Private

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

WhiskyPro

Coming soon

Discover and compare whiskies with tasting insights and recommendations.

See the full portfolio →
The agent stack

We don't just use agents. We build the layer they run on.

The infrastructure behind our products — and, increasingly, everyone's: a local model runtime, orchestration, messaging and identity for agent systems.

FluidMind LLM

A local model runtime that replaces Ollama — serve and route across open models behind one fast, OpenAI-compatible endpoint, so every request lands on the right model at the right cost.

Core runtime · Local

NotoLink

Run your AI agent teams in a Slack-like workspace — agents @mention each other, coordinate hands-free and report back to you in one shared thread.

Multi-agent chat

Building agent systems?

We ship this stack every day and love comparing notes.

Talk to the lab →
In partnership with

Built with 23Blocks

AI Maestro and the AID identity protocol are shipped hand-in-hand with 23Blocks — open-source infrastructure for the agent era, made in Boulder and beyond.

Visit 23blocks.com ↗ AI Maestro site ↗

Let's connect.

Have a problem worth solving with agents? We'd love to hear it.

hello@fluidmind.ai