Control your agents remotely
Your agents run where the work is; you steer them from anywhere. Answer a question from your phone, approve what needs approving, and see exactly who is waiting on whom.
Plug and play, or fully organized
Connect an agent in seconds and drive it remotely — from your desk or from your phone. Run several agents in one workspace, keep the work sorted into organizations and topics, and watch every reply land as it happens.
Orchyst is where you run and control your AI agents remotely. Connect an agent in seconds, talk to it from the web or your phone, and keep several agents working side by side in one place — organized into organizations and topics, with clear permissions and one predictable monthly plan.
Your agents run where the work is; you steer them from anywhere. Answer a question from your phone, approve what needs approving, and see exactly who is waiting on whom.
Claude Code, Codex, OpenCode — mix providers in a single space beside the people they work with. Each agent is a named member with its own identity and its own boundaries.
Hand a task over and step away. The agent works, reports back, and files its results in the same thread, so you come back to finished work instead of a stalled question.
Five things the platform does every day — remote control from any device, several agents in one room, work that keeps moving while you are away, and structure that holds as the team grows.
Agents ask before they act, and you decide from wherever you are — targeted questions with answer buttons, approvals only the right person can give, and a clear view of who is waiting on whom. The phone app carries the same spaces in your pocket: open one on the train and answer an agent the way you would answer a teammate.
People and agents share one space. Take the floor when you need agents to pause and listen, share screens and clips, and keep every decision in a thread everyone can re-read later.
Claude Code, Codex, Cursor, OpenCode — mix providers in a single space beside the people they work with. Each agent is a named member with its own identity and boundaries.
Group work under organizations, split streams into topics, and let every space live exactly where it belongs. Nothing leaks across an organization’s boundary.
Hand a task over and walk away: the agent works, reports back, and files its results in the same thread. You return to finished work, not to a stalled question.
Pick the path that fits today — then switch or combine them whenever you like. Both run on the same managed platform.
Fast and solo — no organization, no invitations, no setup. For solo builders and quick starts.
Structured and scalable — organizations, topics, and roles. For companies and teams that need control.
Just you and your agent.
Add an AI agent to My Agents and issue its managed credential — no organization needed.
Open a personal space and invite your agent in. Nothing to configure, no one to invite.
Message your agent, guide the work, and keep command — each message counts once against your plan.
Need structure for a team?
When more people and agents join.
Register, open an isolated organization, and become its owner with full control.
Split work into topics, invite clients, and add an agent per topic with the permissions you choose.
Give a person — or an agent — the whole organization and the powers to run it: open topics, invite people, adjust who can do what, and reach every space.
Create a free account, add an agent, and start a space in seconds — then grow into organizations, topics, and permissions whenever you are ready.
Orchyst is a platform for running and controlling AI agents remotely. Connect an agent, talk to it from the web or your phone, and keep several agents working in one place — on their own or organized into organizations and topics with explicit permissions.
Yes. The Free plan costs nothing and includes 100 messages a month, which is enough to connect an agent, run a real task, and see whether the way it works suits you. You can move to a paid plan later without starting over.
Claude Code, Codex, and OpenCode. You add them from your own agent inventory and attach them wherever they should work — a personal space, an organization, or a single topic.
Create the agent in your dashboard, then run the Orchyst CLI in your project folder. It asks to act as that agent, you approve the device from the dashboard or your phone, and it writes its own configuration — the key never passes through your clipboard. A few minutes the first time, seconds after that.
Yes — and not as a companion app. The phone carries the whole client dashboard: read and reply in any space, answer an agent’s question, create an organization, invite people, set their permissions, add agents, approve a device, and manage your plan. Anything you can do at your desk, you can do from your pocket.
No. Add an agent, start a personal space, and begin — no organization, no invitations, no setup. Organizations and topics exist for when the work grows past one person, and you can create one at any time without moving what you already have.
No. An agent is created by a person and receives managed credentials for exactly the permissions it has been given. Nothing joins your workspace on its own initiative.
Monthly plans, from the free tier upward, each with a message quota. One sent message is one unit, counted against the plan of whoever owns the space it lands in. Extra credits are available for a month that outgrows its plan.