What is Minion Code in Glueprint?
Minion Code is an AI code assistant built on the Minion framework and pre-configured for development tasks. It bundles more than 12 built-in tools spanning file operations, system command execution, and web search, and adds MCP tool loading, conversation history, and built-in security checks for dangerous operations. Written entirely in Python, it exposes a CLI, an async/sync programming API, and stdio protocol servers with documented Zed editor integration. Models are user-configurable. It is licensed under AGPL-3.0.
An enhanced AI code assistant built on the Minion framework with rich development tools.
Minion Code connects over the open Agent Client Protocol. One generic adapter implements the protocol's client side, so Minion Code gets the same surfaces as every other harness.
Everything below works with the Minion Code 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 Minion Code 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.
Open the ACP catalog
On each execution host, open Settings -> Agents -> Browse ACP catalog and choose Minion Code.
Install and initialize
Glueprint installs the registry distribution for Minion Code, starts it, and completes the ACP initialize handshake.
Start a project session
Choose Minion Code from a project or worktree and use the capabilities reported by that installed build.
How the connection works.
Glueprint adds orchestration and shared surfaces without taking ownership of the coding agent or its provider account.
Glueprint finds the Minion Code binary you installed and spawns it, then speaks the Agent Client Protocol — JSON-RPC 2.0 over stdio — to drive it. Same CLI, same authentication; Glueprint just wraps the session.
Message chunks, tool calls, and tool-call updates from Minion Code arrive as protocol notifications and render as the same live, typed timeline every Glueprint session gets — watchable from desktop, browser, or phone.
When Minion Code 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.
Because Minion Code speaks ACP, adding it is a catalog entry, not an engineering project — the same adapter runs every other agent in the registry, so you can tile them side by side.
Capabilities and discovery.
The status labels separate guaranteed integration behavior from features owned or announced by the installed agent.
| Capability | Status | Behavior |
|---|---|---|
| Python assistant built on the Minion framework | Runtime | Confirmed when the installed agent connects. |
| 12+ built-in tools with security checks | Runtime | Confirmed when the installed agent connects. |
| MCP tool loading and conversation history | Runtime | Confirmed when the installed agent connects. |
| CLI plus async/sync programming API | Runtime | Confirmed when the installed agent connects. |
| AGPL-3.0 licensed, configurable models | Runtime | Confirmed when the installed agent connects. |
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 Minion Code 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 Minion Code sessions side by side, each in its own git worktree, with diffs, history, and a three-pane conflict resolver alongside.
Tile Minion Code next to Claude Code, Codex, and the rest of the ACP fleet in the Command Center. The protocol differs; the surface doesn't.
Promote it to an assistant: persona, constitution, long-term memory, and a daily journal on disk, loaded into every wake.
Wake it 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 Minion Code 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
Can I run Minion Code with Glueprint?
Yes. Minion Code is registered in the official Agent Client Protocol registry, and Glueprint implements the protocol's client side. It spawns the Minion Code CLI you already installed and drives it over JSON-RPC 2.0 — adding live sessions, inline approvals, worktrees, and remote control.
Do I need a separate Minion Code subscription or API key?
No. Glueprint doesn't resell model access. Minion Code authenticates exactly the way its vendor designed — its own login, subscription, or API key. Glueprint spawns the binary and speaks the protocol; it doesn't sit between you and the model provider.
Can I run Minion Code 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 Minion Code sessions live, lets you send follow-ups, and handles permission approvals from anywhere.
Can I run Minion Code 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.