-->

-->

Introducing Poolside Desktop Assistant, for macOS — Poolside

Table of contents<br>Coding agents have outgrown the chat box<br>One workspace to run it all<br>Hand work from one agent to another<br>Run a fleet, not a queue<br>A layout for operating, not chatting<br>Your history comes with you<br>Chat mode, for thinking<br>Connectors out of the box<br>Fully offline, if your Mac can take it<br>Get started

strong]:text-secondary prose-a:text-pri-800 prose-a:font-normal prose-a:hover:text-pri-700 prose-pre:p-8 prose-li:[&>p]:my-4 prose-a:underline-offset-4 prose-ul:text-list col-span-1 col-start-1 row-start-1 min-w-0 max-w-[unset] svelte-18z5kmr">Most of our time at Poolside is spent building models. But a capable model is not a useful coding agent on its own. It needs a harness that gives it tools and runs the agent loop, and an interface that lets a developer direct, inspect, and review the work.<br>For the past year, our team has done its daily work inside tools we built for ourselves: pool, our agent harness and CLI, and the interfaces around it for running agents wherever we happen to be working.<br>Today, we’re making those interfaces available to everyone.<br>Poolside Desktop Assistant is a macOS app for running multiple coding agents across projects and repositories. The Poolside Assistant extensions bring the same experience into VS Code and Visual Studio.

Out of the box, Poolside Assistant pairs pool with Laguna S 2.1, making this the most direct way to work with our models today.<br>But the Assistant is not limited to the Poolside stack. It is built on the Agent Client Protocol, or ACP, so compatible agents can run alongside pool. You can bring your existing Claude Code, Codex, or Gemini subscription, point pool at an OpenAI-compatible inference endpoint, or run an open-weight model locally on your Mac.<br>We don’t think developers should have to adopt one company’s entire stack to use a good model or agent. Our goal is to build the best vendor-agnostic place to work with coding agents.<br>Coding agents have outgrown the chat box<br>The models got good fast. What we wrapped around them didn’t move nearly as quickly.<br>A single chat column is fine when you’re asking a question or getting help with a function. It starts to creak the moment an agent is actually doing the work: reading through a repository, working in the terminal, changing files, running the tests, fixing what it broke, and staying at it for hours. One scrolling column was never built for that, and you feel it.<br>The real unit of work isn’t a message anymore, it’s a session, tied to a repository, a branch, its tools, its permissions, a runtime, and everything that’s happened so far. Once you see it that way, the interface has to change too.<br>And there is rarely only one session. You might have one agent implementing a feature, another investigating a bug, and a third reviewing the first agent’s work. Your role is no longer just to prompt them. It is to provide context, follow their progress, inspect what they produce, intervene when necessary, and decide what happens next.<br>That shift shaped the core design decision behind Poolside Assistant: the interface, the agent harness, and the model should remain separate and be composable.<br>Poolside Assistant uses ACP to connect the interface to the harness and, through it, the model. Any ACP-compatible harness can plug in without routing model calls through Poolside or changing its configuration. Claude Code and Codex continue to use the models and configurations they support. pool can run Laguna or connect to any OpenAI-compatible inference endpoint.<br>Within one workspace, you can run several agents at once, even across different harnesses. Each task can be isolated in its own repository or worktree, with conversations beside the relevant terminals, files, and diffs. You can also pass a session from one agent to another with its context intact.<br>It is an interface for orchestrating agents, not another chat box.<br>One workspace to run it all<br>Hand work from one agent to another<br>Different agents have different strengths. One might be great at planning while another is better at grinding through a long implementation. Every subscription also has a ceiling, usually discovered halfway through a task.<br>Conversations in Poolside Assistant are not welded to the agent that started them. You can hand off a conversation along with its context. Have one agent write the plan and another implement it. Ask Claude Code to review what pool built. Hit a Fable rate limit at 4 p.m. and carry on with another harness.<br>Because everything speaks ACP, the handoff is seamless.

Poolside Desktop Agent Handoff<br>Conversations in Poolside Assistant are not welded to the agent that started them. You can hand off a conversation along with its context. Have one agent write the plan and another implement it. Ask Claude Code to review what pool built. Hit a Fable rate limit at 4 p.m. and carry on with another harness.Run a fleet, not a queue<br>An interface that makes you wait for...