OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Infrastructure

Orb

Orb is a macOS and iOS client for connecting AI providers, machines and agent harnesses, launching agents across local, private remote and supported cloud environments, and managing their project conversations. Its sandboxed.sh backend stores project and mission records and coordinates remote execution.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Orb — OpenViST project profile in Agent Infrastructure.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Orb when you need a client to coordinate coding-agent work across local computers, remote machines or supported cloud-agent services, and to keep missions and follow-ups organized by project.

Who it is for

  • Developers running coding agents against local files and tools.
  • Teams or individuals coordinating agents across their own servers and remote machines.
  • Users who want to inspect projects and continue agent conversations from an iOS client.

Documented uses

  • Connect provider subscriptions or API keys and local hardware to machines.
  • Select a harness, model and execution mode to launch coding-agent work.
  • Follow runs, steer them with prompts or queued follow-ups, and ask side questions with shared workspace context.
  • Organize missions, skills and shared context by project, then review or continue work across clients.
Before you choose

Requirements & limits

  • Orb is the client; sandboxed.sh is the backend and must be run separately.
  • Execution modes differ: local agents use the computer's files and tools, remote agents use configured machines, and cloud agents rely on separate provider connections.
  • The documented desktop stack is Tauri and SolidJS; the iOS client uses SwiftUI, with a Rust backend for project, mission and remote-node coordination.
  • CLIProxyAPI Plus can route model inference for coding agents, but does not replace the separate sign-in or API setup for managed cloud agents.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up Orb with the sandboxed.sh backend

Prepare the backend and client, connect an execution environment, and reach the point of launching an agent.

Before you start

  • A backend host for sandboxed.sh.
  • An Orb desktop or iOS client.
  • An execution environment and inference provider for the agent you intend to use.

Steps

  1. Run sandboxed.sh using its Docker guide or native Linux guide.

  2. Build the Orb desktop client or iOS app, enter the server URL and sign in.

  3. Set up local harnesses, register remote machines, or connect a cloud-agent account; configure inference providers for the models you want.

  4. Create a project, choose an execution mode, write a task and launch an agent.

Expected outcome

An agent runs in the selected execution mode, with its conversation and results grouped in a project.

Guide limitations

  • The documented setup does not specify commands, system requirements or provider-specific credentials.
  • Cloud agents use separate service adapters; connecting a model-inference proxy account does not sign in to ChatGPT or create a Cursor Cloud API account.
Documentation 1 ↗Documentation 2 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
Th0rgal/orb · Official homepage title · retained in its source language
How we review sourcesSuggest a correction