Building osone.ai and many other agentic experiments. Prev Botmock (acq). Angel investor, advisor. Fuelled by chai.
Toronto, Canada / Bay Area, CA
- Tweets 2,520
- Following 3,523
- Followers 1,979
- Likes 231
Your computer should have an FSD button.
You’ve been working on something for 3 hours. It has watched the context accumulate across your terminal, browser, Slack, docs, email and agents.
You need to leave.
Instead of stopping everything, you press:
FSD
Your computer takes over the work.
Not blindly clicking around. It understands the objective you were working toward.
You could tell it:
“Get as far as you can on this while I’m gone. Ask me for approval only when necessary.”
When you return, it gives you a replay:
Here’s what I did.
Here’s what changed.
Here’s where I got stuck.
Here’s what needs your decision.
AI assistants are still designed around conversations.
I think the much bigger idea is continuity of work.
1
2
151
You can try it today with Mola Cloud at cloud.mola.sh and run it locally Mola.sh (open source)
2
266
Or you can bring your own agents harnesses like Claude code, codex, OpenClaw, or Hermes and more into your existing slack with crewx.ai
we’re excited to share that we’ve raised $20M (from Accel, Index, & Emergence) to build the 'ai-native Slack' you've all been craving
TLDR; ando is a team messaging platform built fresh, from the ground, up for a world where agents act as real collaborators alongside us.
we have teams using us across 15 countries, and spanning industries like software, financial services, real estate, & more
request access if any of this resonates 💌
116
This is pretty neat. Learned a lot about how AI agents are using my products and how can I improve the experience for my users and agents.
Today, we are launching Agent Detection-1, the first system-one model built to classify visitors on your web platform.
Agents are already on your web platform. Muse, Instinct, Claude Code, Codex, and thousands more are booking, buying, and filling out forms. Behind each agent could be a real customer.
Cloudflare, Akamai, and other bot tools are built to block agents. Analytics like Amplitude, Datadog, and Google Analytics can't tell them apart from people.
We want to detect agents, figure out which ones are useful, and redirect them to where they can actually get things done.
Agent Detection-1 tells you who's at the door, the moment they arrive:
> Person or agent, and which agent
> Send useful agents to your MCP server, llms.txt, or agent card
> Stop the bad ones, like scrapers and credential stuffers
> Every visit gets logged on your Resemble dashboard
Just add a one-line script and find out who's visiting your website. Starting at just $1 per 1,000 visitors.
1
5
229
You can do this today with osone.ai. It’s been a huge unlock for me to run the entire operation for my saas products from slack.
112
Happy to announce that I have successfully integrated Jev by @typesafeai into my toothbrush.
It makes a calibrated decision on every tooth in under 100ms.
The future is here.
1
2
91
Yup. Agents would love using the power of Linux. @OmarchyLinux has already shown us what could that unlock.
With Mola you can just give your agents access to Omarchy.
2
116
Jev from @typesafeai is now integrated in all of my products. They do feel snappier and more reliable since those decision points are now powered by Jev.
1
2
143
Giving my agent access to @OmarchyLinux has been such a delightful hack. They are more efficient when using the os and overall experience seems to be very smooth.
3
419
Is there an app like Codex but that can use other harnesses like Pi, opencode, codex, Claude etc??
I want the same dev experience as Codex. With built in browser, terminal etc.
2
150
I have seen too many people spend huge amount of time + $$$ trying to build their product on @Replit and getting stuck on last mile.
59
Turns out @dhh's @OmarchyLinux isn’t just a great environment for humans.
It’s pretty damn good for agents too.
I wanted my crewx.ai agents to use Omarchy for computer-use, so I built Mola 🐟
Spin up an Omarchy machine on demand.
Control it over REST API + MCP.
Let your agent actually get to work.
Fast, persistent, agent-friendly.
mola.sh
it’s open source.
Here’s how it works 👇
1
3
170
Building your own agent runtime?
There’s a REST API too.
Create / start / stop / delete machines, run commands, read/write files, take screenshots and control the desktop.
That’s how I’m plugging Mola into crewx.ai.
Agent needs a computer → Mola gives it an Omarchy machine → agent gets to work.
1
21
Can't wait to see what you all build with this....
Docs + source:
mola.sh
12