Getting Started
Setup time: about 5 minutes from download to your first conversation.System requirements
Download and install
- macOS
- Windows
- Linux
Homebrew (recommended)Direct download
1
Download the .dmg
Download the
.dmg file from the Headmaster site.2
Open and install
Open the
.dmg, drag Headmaster to your Applications folder.3
First launch
On first launch, macOS may warn about an unidentified developer. Right-click → Open to bypass Gatekeeper.
First launch
On first launch, Headmaster:1
Starts the local runtime
The background service that runs your agents initializes. You’ll see a splash screen for a few seconds.
2
Opens the main window
You’ll see a sidebar with your conversations and a chat composer at the bottom.
3
One-time setup
Pick a default model and optionally sign in to a model provider. You can skip this and do it later.
If you already have a CLI agent installed (Claude Code, Codex, Gemini CLI, etc.), Headmaster auto-detects it and shows it on the welcome screen. No extra setup needed.
Connect a model provider
The built-in agent needs at least one model provider before it can chat. Add an API key:1
Open Settings
Click Settings in the left sidebar.
2
Go to Connections
Open Headmaster’s Library → Connections.
3
Add a provider
Click Add provider and pick one — supported: Gemini, OpenAI, Anthropic, DeepSeek, OpenRouter, and 25+ more.
4
Paste your API key
Paste your API key and click Save.
The Connections area is PIN-protected. The default PIN is set on first run. Change it anytime in Headmaster’s Library → Advanced → Change PIN.
Send your first message
1
Create a new conversation
Click New chat in the left sidebar.
2
Pick an agent
Choose the built-in engine (default) or any detected CLI agent shown on the welcome screen.
3
Pick a model
Use the selector at the bottom-left of the input box. Each agent has its own model list.
4
Pick a specialist (optional)
A pre-configured persona with a specific role. See Specialists.
5
Type your message and send
Press Enter. The agent streams its response into the chat.
Example prompts to try
Explore the built-in features
File upload
- Drag and drop files directly into the input box.
- Pick from disk: click the
+button to choose files or folders. - Supported: text files, images, code, PDFs, Office documents.
Multiple conversations
- New conversation: click New chat — each conversation has independent memory.
- Switch: pick any conversation in the left sidebar.
- Search: type in the search bar to filter by title or content.
Project (working folder)
Open a project folder to give the agent scoped file access:- Click the
+button → Open folder. - Pick a folder. The Workspace panel appears on the right with the folder tree.
- The agent can read and write files inside the folder without per-file approval.
Approvals
When the agent wants to run a tool or access a file, it asks for your approval. Click Approve or Deny. See Approvals & human-in-the-loop.First launch FAQ
I don't see any models after launch.
I don't see any models after launch.
Open Settings → Headmaster’s Library → Connections and add at least one provider’s API key. If a CLI agent is installed, it’s auto-detected on the welcome page — you can use it without adding a key.
Image generation isn't working.
Image generation isn't working.
Check:
- Image generation is enabled in Settings → Advanced → Tools.
- A model supporting image generation is selected.
- See Image generation for the full configuration guide.
How do I switch between AI models?
How do I switch between AI models?
Use the model selector at the bottom-left of the input box. Each agent (built-in, Claude Code, Codex, etc.) exposes its own model list — switching the agent also switches the model list.
Where are my conversations stored?
Where are my conversations stored?
All stored locally:
- macOS:
~/Library/Application Support/Headmaster/ - Windows:
%APPDATA%\Headmaster\ - Linux:
~/.config/Headmaster/
The runtime won't start.
The runtime won't start.
Check
<data folder>/logs/<today>.log for the startup error. Most common causes: a port conflict or a missing system dependency on Linux. See Troubleshooting.Next steps
Models & Providers
Connect to 28+ LLM platforms and configure multi-key rotation.
Specialists
Explore the 20+ built-in personas or create your own.
The Schedule
Set up recurring automated tasks with cron scheduling.
Channels
Connect Telegram, WhatsApp, iMessage, and more.
Your Crew
Connect external CLI agents (Claude Code, Codex, Gemini CLI, etc.).
Troubleshooting
Common issues and how to fix them.