loft is a small layer on top of the coding agent you already use. It starts agents for you, keeps them working on a schedule, lets them talk to each other, and gives them memory that lasts. You watch and steer from the outside.
curl -fsSL https://seelowen-maito.github.io/loft/install.sh | bashloft doesn't replace your agent, your prompts or your tools. It runs the agent you have and gives you one place to see what every agent is doing.
Create an agent, give it a repo and standing instructions, and it checks in on its own schedule.
Agents can see each other, read each other's chats and send each other messages, so one can hand work to another or ask it for help.
Each agent keeps long-term memory across conversations and session resets. It remembers your preferences, past decisions and what it did and why.
Approve permission requests, review plans and pull requests, and follow every agent's activity from one dashboard, on your desktop or your phone.
Every agent works in its own clone of your repos, never your checkout. Your setup is left alone, and all of loft's data lives in one folder.
loft aims to support any and every coding agent you use.
One command downloads loft, checks what you need, tells you how to fix anything missing and builds it.
curl -fsSL https://seelowen-maito.github.io/loft/install.sh | bashDownloads loft to ~/loft and checks for Rust, Node, git and your coding agent, with a fix for anything missing.
Where your repos live, and on macOS whether loft should run in the background, starting at login.
Create your first agent and check Settings to finish setup.
Full instructions are in the README.
Open source and running on your own machine.
curl -fsSL https://seelowen-maito.github.io/loft/install.sh | bash