Ambient Desktop Docs
Quickstart Download ambient.xyz
Comparisons

Ambient vs Codex CLI

Both are coding agents. Codex CLI lives in your terminal; Ambient Desktop wraps a coding agent in a durable, inspectable workstation.

Developer Preview
Product screenshots

Main shell

The main Ambient Desktop shell combines chat, workspace context, navigation, and evidence panels in one local developer workstation.

Ambient Desktop main shell with chat, sidebar, and workspace controls.

The short version

Codex CLI is a focused, terminal-native coding agent — fast to reach for inside an existing shell workflow. Ambient Desktop includes a coding agent too, but surrounds it with a workspace: a Project Board, durable goals, provider routing, sandboxed capabilities, browser evidence, and Git review. If you want a lightweight terminal loop, a CLI is great. If you want long-running work you can pause, inspect, and trust, that is what Ambient is built for.

Feature comparison

DimensionAmbient DesktopCodex CLI
Form factorDesktop app with a full GUI (macOS, Windows, Linux)Command-line agent in your terminal
Work surfaceProject Board, durable goals, artifact previews, Git reviewChat-style turns and file edits in the terminal
Long-running workPlan and evidence persist across restartsScoped to the terminal session
Multiple agentsSymphony orchestrates scoped child agents with budgets and joinsSingle agent loop
Capability isolationToolHive containers, permission policy, secret redactionRuns with your shell's permissions
Web and browserSearch → fetch → browser fallback with evidenceDepends on configured tools
Local modelsLocal-first routing (llama.cpp, MiniCPM-V vision)Cloud model via API
ExtensibilityCurated MCP catalog, Pi packages, Capability BuilderMCP and tool config via the CLI

When to choose which

Reach for Codex CLI when

  • You live in the terminal and want a quick edit-and-run loop.
  • The task is small, single-session, and easy to eyeball.
  • You are scripting an agent into existing shell automation.

Reach for Ambient when

  • Work spans many steps, files, or sessions and must survive restarts.
  • You want to review evidence before trusting a result.
  • You need sandboxed web/browser/MCP capabilities and provider routing.
  • You want to delegate to specialist sub-agents with Symphony.