What is Gemini CLI in Glueprint?
Gemini CLI connects over the open Agent Client Protocol — the integration path Google ships in the CLI itself — with first-class detection and capabilities in Glueprint.
Everything below works with the Gemini CLI you have today — no migration, no new account for the model, no lock-in. Uninstall Glueprint and your terminal workflow is exactly as it was.
Set up Gemini CLI on a host.
Installation is host-specific: repeat these steps anywhere this agent should execute. Portal and mobile can control the session afterward, but the process remains on that host.
Install and authenticate Gemini CLI
Install the official package on every host where sessions should run, then complete Gemini's own authentication flow.
Detect the CLI in Glueprint
Open Settings -> Agents -> Gemini. Leave CLI Path on Auto-detect, choose Detect, and confirm the resolved path and version.
Start an ACP session
Open a project or worktree, create a session, choose Gemini, and use the capabilities reported by the connected CLI.
npm install -g @google/gemini-cli
gemini --versionHow the connection works.
Glueprint adds orchestration and shared surfaces without taking ownership of the coding agent or its provider account.
Glueprint finds the gemini binary you already installed, probes the version, and spawns it. Your Google login or API key and your configuration come along, because it's the same CLI you run in the terminal.
Gemini CLI speaks the Agent Client Protocol natively, so Glueprint drives it the way Google intended: JSON-RPC 2.0 over stdio. Gemini gets first-class detection, a curated capability profile, and its own brand treatment across every surface.
Message chunks, tool calls, and tool-call updates arrive as protocol notifications and render as a live, typed timeline — watchable from desktop, browser, or phone instead of terminal scrollback.
When Gemini asks to write a file or run a command, the protocol's permission request surfaces as an inline approval card on whatever device you're holding. Approve, deny, or auto-allow per tool.
Capabilities and discovery.
The status labels separate guaranteed integration behavior from features owned or announced by the installed agent.
| Capability | Status | Behavior |
|---|---|---|
| Structured session stream | Supported | ACP messages and tool-call updates render in the shared timeline. |
| Permission responses | Runtime | Available when the connected Gemini build advertises protocol approvals. |
| Models and modes | Runtime | Provider/model and mode options are discovered during initialization. |
| Slash commands | Runtime | Shown when Gemini reports command discovery support. |
| Session load or resume | Runtime | Availability depends on the installed Gemini version. |
| Image input | Runtime | Enabled only when advertised by the connected build. |
| Reasoning-effort control | Not exposed | The ACP adapter does not add a separate reasoning-effort knob. |
Authentication, ownership, and limits.
Glueprint is the environment around the agent. Credentials, model access, and vendor-specific behavior stay where their owner designed them.
Watch every prompt, tool call, and diff stream in real time — desktop, web portal, iOS and Android. The session runs on your machine; the view follows you.
Permission prompts arrive as approval cards wherever you are. Kick off a refactor at your desk, approve the file writes from the couch.
Run several Gemini sessions side by side, each in its own git worktree. Built-in worktree management, diffs, and a three-pane conflict resolver keep them from stepping on each other.
Tile Gemini sessions from your laptop, your desktop, and a homelab box into one Command Center mosaic — next to Claude Code and Codex if you run those too.
Promote Gemini to a persistent assistant: persona, constitution, long-term memory, and a daily journal on disk, loaded into every wake.
Wake Gemini on cron: triage the inbox every 30 minutes, sweep PRs at 9am, run the nightly cleanup. Quiet hours and watermarks prevent re-fires.
Messages, sessions, and output tokens computed from session logs — compare Gemini against Claude Code, Codex, and your other ACP agents.
Remote viewing rides AES-256-GCM envelope encryption. The relay routes; it cannot read.
Common questions
Does Glueprint replace the Gemini CLI?
No. Glueprint is an Agentic Development Environment that hosts Gemini CLI. It spawns the official CLI you already installed and adds the surfaces around it: live session streaming, inline approvals, parallel worktrees, scheduling, memory, and remote control.
Do I need an API key or a separate Gemini subscription?
No. Glueprint doesn't resell model access. Sessions run through the gemini CLI's own authentication — your existing Google login, Gemini subscription, or API key is exactly what gets used.
What does "over ACP" mean here?
Gemini CLI ships native support for the Agent Client Protocol — an open standard for editor-to-agent communication. Glueprint speaks the protocol's client side, so Gemini connects the way Google built it to, while still getting first-class detection and its own capability profile.
Can I run Gemini from my phone?
Sessions always run on your machines — a laptop, a desktop, or a server with the headless daemon. The iOS and Android app streams them live, lets you send follow-ups, and handles permission approvals from anywhere.
Can I run Gemini next to Claude Code and Codex?
Yes — that's the point. Each harness is an adapter; sessions from all of them tile into the same Command Center, share the same task boards, and roll up in the same per-harness analytics.
Is my session content private?
Yes. Remote viewing routes AES-256-GCM-encrypted envelopes through the relay, which stores a wrapped key it cannot open — decryption happens on your devices. On the free local tier, session content never leaves your machine at all. See security.