What is GLM Agent in Glueprint?
GLM-ACP-Agent is an Agent Client Protocol implementation written in TypeScript that uses Z.AI / Zhipu AI's GLM model family as its reasoning core, defaulting to a GLM thinking mode and supporting several GLM variants. It streams responses over stdio, supports tool calling across many reasoning turns, and ships six built-in tools covering file I/O, directory listing, shell commands, web search, web reading, and image analysis. It is licensed under Apache 2.0 and published to npm.
ACP agent powered by Zhipu AI's GLM Coding Plan models (glm-5.1, glm-5-turbo, glm-4.7, glm-4.5-air). Supports streaming, tool calls, mid-session model switching, image input via Z.AI Coding Plan Vision MCP, and session load/fork/resume with on-disk persistence.
GLM Agent connects over the open Agent Client Protocol. One generic adapter implements the protocol's client side, so GLM Agent gets the same surfaces as every other harness.
Everything below works with the GLM Agent 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 GLM Agent 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 GLM Agent.
Install and initialize
Glueprint installs the registry distribution for GLM Agent, starts it, and completes the ACP initialize handshake.
Start a project session
Choose GLM Agent 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 GLM Agent 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 GLM Agent arrive as protocol notifications and render as the same live, typed timeline every Glueprint session gets — watchable from desktop, browser, or phone.
When GLM Agent 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 GLM Agent 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 |
|---|---|---|
| TypeScript agent built on the GLM model family | Runtime | Confirmed when the installed agent connects. |
| Default GLM thinking mode, multiple variants | Runtime | Confirmed when the installed agent connects. |
| Six built-in tools including shell and web | Runtime | Confirmed when the installed agent connects. |
| Session persistence with load, fork, and resume | Runtime | Confirmed when the installed agent connects. |
| Apache 2.0, requires Node.js 20+ | 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 GLM Agent 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 GLM Agent sessions side by side, each in its own git worktree, with diffs, history, and a three-pane conflict resolver alongside.
Tile GLM Agent 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 GLM Agent 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 GLM Agent with Glueprint?
Yes. GLM Agent is registered in the official Agent Client Protocol registry, and Glueprint implements the protocol's client side. It spawns the GLM Agent 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 GLM Agent subscription or API key?
No. Glueprint doesn't resell model access. GLM Agent 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 GLM Agent 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 GLM Agent sessions live, lets you send follow-ups, and handles permission approvals from anywhere.
Can I run GLM Agent 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.