Getting Started
Triggerfish is a secure, multi-channel AI agent platform with deterministic policy enforcement below the LLM layer. It connects to every messaging platform you already use -- Telegram, Slack, Discord, WhatsApp, Email, WebChat, and the CLI -- while enforcing data classification rules that the AI cannot bypass, override, or influence.
Whether you are an individual who wants a powerful personal AI assistant with real security guarantees, or an organization that needs auditable policy enforcement across employee-agent interactions, Triggerfish gives you both the integration breadth and the controls to use AI with confidence.
Triggerfish is open source (MIT licensed), runs locally on your machine, and supports multiple LLM providers including Anthropic Claude, OpenAI, Google Gemini, local models via Ollama, and OpenRouter.
Next Steps
| Page | Description |
|---|---|
| Installation | Install Triggerfish on macOS, Linux, or Windows |
| Quick Start | Set up your first agent in under 5 minutes |
| Configuration | Full configuration reference for triggerfish.yaml |
| SPINE and Triggers | Define your agent's identity and proactive behavior |
| CLI Commands | Complete command reference for the triggerfish CLI |