Supported agents

Mastery HQ drives thirteen agent types. Eight are CLI agents that run locally with your own accounts; OpenRouter, Qwen, Kimi and Local models are HTTP backends (any model, no CLI); Hermes is the built-in orchestrator. Settings → Agents shows live detection of what’s installed.

Agent	Runs via	Notes
Claude Code	claude CLI	The default agent brand
Codex	codex CLI	OpenAI’s coding agent
Cursor Agent	cursor-agent CLI	No native Windows build yet - runs via WSL (Settings → Agents links the docs)
Gemini CLI	gemini CLI	Google; multimodal models
Aider	aider CLI	Pair-programmer; one-click install (the app fetches a private Python via uv - no admin, nothing touches your system)
GitHub Copilot CLI	copilot CLI
Grok Build CLI	grok CLI	xAI’s coding agent; signs in with your xAI key (XAI_API_KEY) or its own grok login
OpenCode	opencode CLI	Open-source agent; a model picker in the window header switches its model per window (opencode run -m)
OpenRouter	HTTP (no CLI)	Any OpenRouter model; needs OPENROUTER_API_KEY
Qwen	HTTP (no CLI)	Alibaba’s Qwen models over OpenRouter - Qwen3.7 Max/Plus/Flash plus the coder and thinking variants; needs OPENROUTER_API_KEY
Kimi	HTTP (no CLI)	Moonshot AI’s Kimi models over OpenRouter - K3, K2.7 Code, K2.6, K2.5, K2 Thinking; needs OPENROUTER_API_KEY
Local model	HTTP (no CLI)	Ollama, LM Studio, Jan (auto-detected, no key) or any OpenAI-compatible endpoint (Msty, Together, Groq, a gateway). See local & custom models
Hermes	Built-in	The orchestrator - dispatches to other agents and drives the workspace

Keeping the CLIs up to date

Settings → Agents shows the published version beside each installed CLI and offers to bring it up to date. Mastery HQ checks in the background every few hours, and a number on the Settings gear tells you when there is something new (see New models and updates).

It never updates anything on its own. Mastery HQ drives these CLIs with specific flags, so an upgrade arriving unannounced could break agent launching with nothing obvious to connect it to - you decide when.

What the row offers depends on how the CLI got there:

• Mastery HQ installed it, or the CLI can update itself (Claude Code, Codex, Grok Build) - Update does it, and the log streams as it goes.
• Something else installed it - a system npm install -g, or the vendor’s own installer - you get the exact command to run instead of a button. A button there would run, report success, and change nothing, because Mastery HQ can only write to its own install area.

Whichever route it takes, the CLI is run once before the update is called done, so an install that finishes “successfully” but leaves a command that won’t start is reported as the failure it is.

New models and updates

When a model comes out for one of your agents, or a newer version of one of the CLIs is published, a number appears on the Settings gear at the top of the window. Settings then opens on Agents, where New for your agents lists what changed:

• A new model (for example Claude Opus 5.5 for Claude Code). Use on N windows switches every window on that CLI to it, from each window’s next message. Dismiss hides it. With no window on that CLI open, pick it later from any window’s model menu.
• A newer CLI version. Update it from the list of installed CLIs just below.

Only models released in the last two months, and newer than the ones the app shipped with, are announced. They come from a public model list, so your plan may not include a new one yet; if an account rejects it, the window falls back to a model it accepts.

Model quick-picks stay current

The model dropdown in an agent window offers that brand’s current models. New models are folded in automatically as they’re published, so the list doesn’t quietly go stale between releases:

• · new - genuinely newer than anything that shipped with the app for that model line.
• · also available - a model line the built-in list never covered. It exists; that isn’t the same as it being newer.

The built-in picks stay first and in order - a few models are deliberately left out because they’re rejected on a normal sign-in - and Custom… still takes any model id your account supports. If the catalog can’t be reached, you get exactly the built-in list.

Codex’s model list and default models

Codex keeps its own list of the models your account can use, and refreshes it itself. Codex windows use that list: the model menu shows exactly what Codex offers you, in Codex’s order, and it is read again every time you open the menu and right after any agent CLI is installed or updated. When a CLI update brings a new model, it is in the menu at once, marked · new.

Settings → Agents → Default models sets the model a window runs when it hasn’t picked its own, for each agent. The same default is used by crews and councils. A window’s model menu says which model “default” will run. Make default on a new model in New for your agents sets it in one click. Leave a default empty to use the agent’s own setting.

How sign-in works

CLI agents use their own authentication (whatever you’ve signed into in that CLI) or an API key from Mastery HQ’s local .env - keys are forwarded to the CLI at launch and never leave your machine. Each brand’s window carries its own accent color so you can tell a Claude from a Codex across the canvas at a glance.

Picking a default

Settings → Agents → Default agent sets which brand “open an agent” spawns.