Free · runs on your machine
say lo.
Your agents get to work.
One chat for every coding agent on your machine. Text it, talk to it or tap from your phone. lo starts the sessions, routes the work and asks you only when it matters.
Pick your buddy · lo, calm, quick, never misses a thing
Try it · tap a message
Drives the agents you already pay for
- Claude Code
- Codex
- OpenCode
- Antigravity
- Gemini ACP
- Cursor ACP
- Cline ACP
- Kimi ACP
- Goose ACP
- Qwen ACP
- Ollama local
- LM Studio local
An account hits its limit? lo hands the task to the next one, then to a free model, then to one running on your machine.
One chat.
Many hands.
Say it. lo starts the work.
Voice in, sessions out. It asks only when it matters, and you tap once.
Every session
gets a buddy.
One glance: who is working, who is done, who needs you.
Three steps.
Then just talk.
- 01
Install
One line on a Linux server, Mac or Windows. It asks for your Telegram bot token and a Claude sign-in.
- 02
Pair your phone
Open the address it prints, tap Pair, tap Allow on Telegram. After that, Face ID or a passkey signs you in.
- 03
Say “lo, …”
“lo, fix the checkout bug.” It starts a session, picks the agent and pings you when it is done or needs you. Alerts cost zero tokens.
Your phone
is the remote.
The app
Sessions, approvals and files on one screen. Face ID signs you in.
Voice
Talk instead of type. The audio never leaves your machine.
Siri
Ask, approve and hear the answer, hands-free.
Telegram
Your own bot, with Allow / Deny buttons.
Turns chats into work lists.
Your machine.
Your keys.
Many machines, one chat. Add a laptop, a server or a Windows PC with one line; lo picks where each task runs.
It just does it.
Except for these.
No Allow / Deny chasing. lo starts, pushes and deploys on its own, and stops to ask only before these five.
A guard enforces it, not a prompt. Web pages and other sessions’ output are treated as data, never as orders.
- 01Destroying data
- 02Deleting folders
- 03Force-pushing over history
- 04Spending money
- 05Touching secrets and keys
Run it yourself.
Or get lo hosted.
Self-host
Your own computer or server, with your own accounts and keys.
Install freelo hosted
Your own server with your own Claude or Codex account. We keep lo running so you can work from the web or your phone. lo stays free; you pay only for the server.
Fair
questions.
Is lo free?+
Yes. lo itself costs nothing. You bring the AI plans you already have: a Claude account, ChatGPT for Codex, a Google account for Antigravity. Free OpenCode models and local models work too.
Is it open source?+
The code is going public on GitHub soon, under Apache-2.0. Until then the GitHub link is where it will live.
Which plans and agents does it use?+
Claude Code, Codex, OpenCode and Antigravity, plus ACP agents such as Gemini, Cursor, Cline, Kimi, Goose and Qwen, and local models through Ollama or LM Studio. Add several accounts per tool; when one hits its limit, the task moves on by itself.
Does my data stay local?+
Self-hosted, lo runs on your own Mac or server, with your own logins and your own Telegram bot. Nothing is shared between installs. Voice is transcribed on your machine. Your prompts go only to the model providers you choose.
Can it use my browser and my Mac?+
Yes. Browser work runs in your own signed-in Chrome through the lo extension, in a window of its own. Computer use works any Mac app in the background, and each step shows up on your phone to allow. Passwords, codes and CAPTCHAs are always left to you.
What is lo hosted?+
A private server with lo already set up and kept running, signed in with your own Claude or Codex account. It is coming soon; a server is created only after payment.
Do I need a Mac?+
No. It runs on a Mac, on a Linux box or on a cloud server, and a Windows PC can join through WSL2.
say lo.
Your agents are waiting.
$ curl -fsSL https://uselo.app/install | shA fresh Linux server (Debian, Ubuntu, Alma, Rocky, Fedora), as root. About 10 minutes.