# Introduction

Noelclaw is an AI-native crypto platform built on top of autonomous agents, real-time market intelligence, and on-chain execution. Users interact with specialized AI agents via chat, automate research shifts, earn credits through an arcade, and manage crypto wallets — all in one interface.

***

## What Noelclaw Does

| Feature           | Description                                                                                 |
| ----------------- | ------------------------------------------------------------------------------------------- |
| **AI Agents**     | 40+ specialized agents for DeFi, news, market data, code, and more                          |
| **Noel Research** | 8-hour autonomous research shifts with Telegram reports                                     |
| **Game to Earn**  | 4 arcade games that pay out credits                                                         |
| **Wallet & DeFi** | Embedded wallet, token swaps, on-chain execution                                            |
| **Automations**   | Schedule agent skills to run on intervals                                                   |
| **MCP Skill**     | Install via `npx @noelclaw/research` in Claude, Cursor, Hermes, Windsurf, or any MCP client |

***

## Two Projects

### `noelapp/` — The Platform

The full application: React frontend + Convex serverless backend. This is the core product.

* **Frontend:** React 19 + TypeScript + TailwindCSS
* **Backend:** Convex (real-time DB + serverless actions)
* **Auth:** Privy (OAuth + embedded wallets for app users)
* **Web3:** Base mainnet, USDC, ethers.js encrypted wallets, 0x Permit2, x402 payment protocol

### `noelclaw.fun/` — The Landing Page

Marketing website only — no backend, no auth. Static React with Framer Motion animations.

***

## Core Features

| Feature                 | Description                                                                                                 |
| ----------------------- | ----------------------------------------------------------------------------------------------------------- |
| **1H Trading Signals**  | BTC and ETH signals generated daily at 08:00 UTC with entry, TP, SL, confidence score, and outcome tracking |
| **Whale Alerts**        | Hourly detection of large on-chain movements, CEX inflow/outflow, and smart money patterns                  |
| **Weekly Recap**        | Every Sunday: full 7-day signal log, win/loss stats, AI performance review, Telegram delivery               |
| **Autonomous Research** | 8-hour research shifts with market data collected every 30 min, reports at 2.5h, 5h, and 8h                 |
| **DeFi Wallet**         | Encrypted Base mainnet wallet auto-created on first use. Swap via 0x Permit2, send ETH/ERC-20               |
| **Telegram Delivery**   | Signals, whale alerts, research reports, and weekly recaps delivered to your personal Telegram bot          |
| **MCP Skill**           | All features accessible as MCP tools in Claude Desktop, Claude Code, Cursor, Hermes, and any MCP client     |

***

## Key Numbers

* 16 MCP tools
* Signals generated once per day (08:00 UTC, 1H timeframe)
* 6-hour signal expiry window
* 8-hour research shifts (3 Telegram reports)
* Weekly recap every Sunday at 23:55 UTC
* Base mainnet — ETH, USDC, USDT, DAI, WETH

***

## Core Philosophy

Noelclaw is built around the idea that AI agents should work **for** users autonomously — not just respond to prompts. Noel generates signals, tracks whale movements, runs market research, and delivers everything on its own schedule via Telegram. Users set it up and let it run.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.noelclaw.fun/getting-started/readme.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.