Leverage Computer

@patrickc 👀

I want some kind of LLM workflow tool. • Ability to manage a set of input files (Markdown or similar), plus other general-purpose context. • With real-time collaboration. (And maybe some concept of snapshots or VCS integration.) • And the ability to create/manage a inference workflows and a stored set of prompts. • Access to general-purpose coding agents (and not just chat models). • Some concept of compiled outputs/inference results (which ideally can be shared externally). Many projects have this feeling: "there is all this stuff, which I want to process/compute over in this iterated way, with some build artifacts being important/worth saving." GNU Autotools x Notion or something. Is anyone building this?

@eimen0 👀

finally macOS desktop app for @leveragecpu 👀

@0xRaduan 👀 when?

too much stuff is cooking

@0xRaduan 👀

gpt image model is good

@0xRaduan 👀

Soon, in every github org:

@0xRaduan 👀

every new startup in 2027 will run on @leveragecpu

@tszzl 👀

is there a better slack for agent age

@danshipper 👀

extremely sick

@xdotli 👀👀👀

guess im one of the cool kids with access to @leveragecpu now

@eimen0 👀👀👀

Internal apps in @leveragecpu run directly on the workspace computer and can be exposed securely to authenticated users. That is the idea behind a multiplayer AI computer where people, agents, automations, and software operating on the same context! Demo below.

@0xRaduan @eimen0 👀

@eimen0 @leveragecpu Will add live cursors next to it

@eimen0 👀

Automations in @leveragecpu are scheduled multiplayer AI sessions with full workspace context. Our daily bugs sweep reads new messages in the bugs channel, creates Linear tickets, opens PRs, and escalates tricky issues. It runs with channel history, repo/filesystem access, integrations, governed tool calls, and full team visibility. Shared context turns into automated work and automated work turns into compounding context.