Skip to content

Online agents overview

Chorus can start and steer agent work on machines you keep online. This page explains that model — what an online agent is, how a project pins work to one, how a single conversation follows an idea, and how you interrupt, resume, or take over — then points to the page where you actually do each thing. For the collaboration workflow those agents run, see The AI-DLC workflow; for the plugin commands they expose, see Commands and skill routing.

An online agent is a chorus daemon process, authenticated with an agent API key, that holds a live connection to Chorus. While it runs, Chorus can reach it to start work, send a follow-up instruction, interrupt a running turn, or resume a stopped one — without you touching the machine.

Each connection is addressed by three things: the agent identity (the API key), the host it runs on, and the working directory (cwd) it serves. One daemon can serve several directories; each registered directory becomes its own addressable target. Chorus shows every connection’s presence — online or offline, with its backend, host, and directory — in Settings → Agents.

Online agents presence panel listing a connection by agent, backend, host, and working directory, with an idle status
The presence panel lists each online connection by agent, backend, host, and working directory.

A project can be fixed to a specific online agent and working directory. Once anchored, agent work started from that project’s UI routes to the same connection and directory, and the working-directory picker is suppressed — you do not re-choose the target each time. See Create a project for how to set, replace, or clear that preference.

A direct idea has a single canonical conversation, and its session id is the idea’s own identifier — so every wake for that idea reaches the same conversation. If you wake the idea from a different working directory, Chorus re-points that one session to the new directory rather than forking a second conversation, so the idea keeps one continuous history.

While an agent is working you can interrupt the current turn, resume a stopped conversation with added context, or take over the conversation from a terminal using its copied session id. These controls act on an existing conversation rather than starting a new one. See Interrupt and resume a session.

OpenClaw connects through the OpenClaw gateway rather than chorus daemon, so it is a gateway-model connection — see OpenClaw.

Each capability of the online-agent model has one place you perform it and one page that documents it in full.

| Capability | Where you do it | Read more | | --- | --- | --- | | Reverse control (interrupt, resume) | The conversation’s Interrupt and Resume controls; the daemon receives them over POST /api/daemon/control | Interrupt and resume a session | | Wake and wake-queue | Start or continue agent work from a project item; a wake for a busy directory is queued until it is free | Start work on a remote agent | | (agent, host, cwd) addressing | Register each working directory when you start the daemon (repeatable --cwd) | Operate the Chorus daemon | | Presence | Settings → Agents shows each connection’s online state, backend, host, and directory | Connect an agent runtime | | Remote start | Pick an online directory, enter an instruction, then Start session | Start work on a remote agent | | Ad-hoc “continue in an online directory” | Hand a new idea to an online agent from the new-idea dialog’s conversational mode | Capture an idea | | Multi-backend (Claude Code, Codex, Kiro) | Choose the backend per connection with --agent | Agent platforms |