Browser Engine · 39 tools · Vision
Wispy

Transform how you build,
automate & ship.

Autonomous AI agents with 90+ tools, browser automation, live vision, multi-model support, and Marathon Mode for multi-day execution.

Wispy
bot

/start

13:42

☁️ Welcome to Wispy!

Your autonomous AI agent. Just talk naturally!

Natural Language Control:

• "Build me a React dashboard" → I'll start working

• "How's it going?" → Check my progress

• "Yes" / "No" → Approve or reject actions

• "Pause" / "Continue" → Control the work

Voice Notes: 🎤

Send voice messages and I'll respond!

/voice - Toggle voice replies

Image Generation:

/image <description> - Generate AI images

Wallet:

/wallet - Check crypto wallet

Examples:

• "Create a landing page with Tailwind"

• "What's the status?"

• 🎤 Send a voice note

• /image A robot playing guitar

I work autonomously and keep you updated! 🚀

13:42

90+

Built-in Tools

1M

Context Tokens

4

Trust Levels

∞

Marathon Days

Quick Start

# Install globally with npm

$ npm install -g wispy-ai

$ wispy setup

$ wispy gateway

Works on macOS, Windows & Linux. The one-liner installs Node.js and everything else for you.

What It Does

Gemini 2.5 + Thinking

Dynamic thinking budget from minimal to high based on task complexity. Gemini 2.5 Pro for deep reasoning, Flash for speed. Multi-model routing with Claude, GPT, Groq, Ollama, and OpenRouter.

@google/genai, multi-provider

x402 + Agentic Commerce

Multi-chain USDC payments on Base, SKALE (gasless), Solana, and Tempo. x402 HTTP-native micropayments, AP2 payment flows, BITE V2 conditional encryption, DeFi token swaps, ERC-8004 reputation, and on-chain audit reports.

x402, viem, ethers, @solana/web3.js

A2A Protocol

Google's Agent-to-Agent protocol for autonomous AI collaboration. Service discovery via /.well-known/agent.json, task delegation with streaming progress, capability querying, and cryptographically signed message exchange.

Google A2A Protocol

Browser Automation

Playwright-powered browser engine with 39 tools. Navigate, click, type, screenshot, scroll, multi-tab sessions. 55 built-in scraper skills for Google, Amazon, LinkedIn, and more. Custom AI-generated automation.

playwright-core, 55 built-in skills

Vector Memory

Semantic memory with Gemini text-embedding-004. SQLite-backed vector store with cosine similarity search. Store facts, conversations, and context that persist across sessions for long-term recall and personalization.

better-sqlite3, text-embedding-004

Multi-Channel

Deploy across Telegram, WhatsApp, Discord, Slack, Gmail, Zoho Mail, and REST API. Inline keyboards, voice notes, file sharing, image generation in-chat, cross-channel file access, and event broadcasting.

grammy, @whiskeysockets/baileys, discord.js

Vision & Media

Webcam capture, video recording, and live vision streaming via ffmpeg. Imagen 3 image generation, screenshot analysis, and real-time frame analysis with Gemini vision.

ffmpeg, @google/genai (vision), Imagen 3

Cron & Marathon Mode

Schedule recurring tasks with cron expressions or natural language. Multi-day marathon research with automatic planning, execution, and progress tracking. Heartbeat monitoring for long-running tasks.

node-cron, marathon service

Works With Everything

WhatsApp
Telegram
Discord
Slack
Gmail
Calendar
Gemini
ClaudeSoon
GitHub
Notion
Spotify
Hue
X
Chrome
Obsidian
Linear
Ethereum
Coinbase
A2A
SKALE
x402
MCP
Chainlink
Base
Solana
Drive
Sheets
View all 40 integrations|See what people built

Skills

12 skills, 66 tools
View all skills

Deep Research

6 tools
Gemini + Vertex

Deep web research, paper analysis, competitor intelligence with citation tracking.

wispy skill add research

Full-Stack Dev

18 tools
Gemini 2.5

Full-stack development with React, Next.js, Node.js, Python. Scaffolding and testing.

wispy skill add codegen

Document Creator

9 tools
Vertex AI

Professional PDFs with LaTeX. Reports, whitepapers, charts and flowcharts.

wispy skill add documents

Web3 & DeFi

16 tools
Base + SKALE + Solana

Multi-chain wallets, x402 USDC payments, DeFi swaps, BITE encryption on Base, SKALE, and Solana.

wispy skill add web3

Resources

Docs

Full documentation

GitHub

View the source

NPM Package

Install via npm

Skills Hub

Download skills

Wispy Platform

Coming Soon

No terminal needed.

The Wispy Platform lets non-technical founders set up AI agents, create workflows, and manage integrations -- all from a visual interface at app.wispy.cc. Get your agent live in under 2 minutes.

Visual Agent BuilderMulti-Model AICrypto Wallets

Agent Wallets

Create and fund dedicated wallets per agent. Connect Base, Coinbase, or MetaMask.

Channel Setup

Connect Telegram, WhatsApp, and more with a few clicks. No terminal.

Workflows & Integrations

27+ integrations, 24+ skills. Drag, configure, deploy.

Bring Your Own Keys

Use your own API keys and pay only hosting, or go fully managed.

Stay in the Loop

Get updates on new features, integrations, and Wispy wisdom. No spam, unsubscribe anytime.