Clawdette — AI agent mascot
Private Beta — powered by Claude AI

Clawdette

Your AI-Powered Multi-Channel Agent

Intelligent conversations powered by Claude AI with 27 built-in tools, MCP integration, and enterprise-grade security.

Built-in tools
27
Channels — Web, WhatsApp, Telegram
3
Unlimited extensions
MCP

Features

AI Conversations

Powered by Claude (Anthropic) - intelligent, context-aware conversations with multi-turn support.

27 Built-in Tools

DateTime, Web Search, TTS, Bash, Email, Calendar, Image Generation, Scheduling and more - ready to use.

MCP Integration

Extend with any MCP server - connect external APIs and services seamlessly.

Enterprise Security

Sandbox VM isolation, external API key management, and per-tenant workspace separation.

Multi-Tenant

Isolated workspaces with individual settings, tools and permissions per user.

Calendar Integration

Connect Google, Microsoft, or Apple calendars - manage events, check availability, and schedule directly.

Tools & Capabilities

27 native tools across 6 categories, plus unlimited MCP extensions.

Standard Tools

4 tools

DateTime, Web Fetch, Memory Search, Memory Get

API-Powered

5 tools

Web Search (Brave), TTS (OpenAI), Image Analysis, Image Generate, Vision

Sandbox

6 tools

Bash, Read, Write, Edit, File Share, Browser

Email

3 tools

Fetch, Send, Search

Calendar

6 tools

List, Search, Create, Update, Delete, Availability

Scheduling

3 tools

Schedule Job, List Schedules, Delete Schedule

Security by Design

AI agents with unchecked access are a liability. Clawdette isolates every layer by default.

Sandbox VM Isolation

All code execution runs in an isolated virtual machine, never on the application server.

External API Key Management

API keys are stored server-side and injected at execution time. The AI model never sees credentials.

Per-Tenant Workspace Isolation

Each user operates in a fully isolated workspace with separate settings, tools, and permissions.

Admin-Controlled Tool Access

Administrators enable or disable tools per tenant. No tool runs without explicit authorization.

No Credential Exposure

API keys stored securely, never passed in prompts or tool descriptions. Zero prompt injection risk for credentials.

Why This Matters

Recent CVEs in open-source AI agents have exposed thousands of instances to credential theft and host compromise. Common architectural flaws include:

Credentials embedded in system prompts, extractable via prompt injection
No sandbox isolation - code execution directly on the host system
Malicious plugins with unrestricted filesystem and network access
No per-user isolation - shared state across all users

Frequently asked questions

Everything you need to know about Clawdette.

What is Clawdette?

Clawdette is an AI agent powered by Claude AI. It chats with you on the web, WhatsApp, and Telegram — and actually gets things done: searching the web, sending emails, managing calendars, running code, and more.

Which channels are supported?

You can talk to Clawdette in the web chat, on WhatsApp, and on Telegram. Your conversations and settings stay in one workspace across all channels.

What can Clawdette actually do?

Clawdette ships with 27 built-in tools across 6 categories: web search, text-to-speech and vision, email, calendars (Google, Microsoft, Apple), scheduled tasks, and a sandboxed environment for code execution and file handling. Via MCP you can connect unlimited additional tools.

Is my data secure?

Yes. Every workspace is fully isolated, code runs in a separate sandbox VM — never on the application server — and API keys are stored server-side and never exposed to the AI model. Administrators control exactly which tools are enabled.

How do I get access?

Clawdette is currently in private beta. Apply with the form on this page — if approved, you will receive a personal invitation by email.

What does it cost?

Clawdette uses transparent, credit-based plans: a free plan to get started plus paid plans and credit packs for higher usage. Details are shown in the dashboard after signup.