Quant72

A Twitter bot built with ElizaOS and TypeScript that tracks crypto Key Opinion Leaders (KOLs) and market data, posting insights to Twitter. This project auto-posts:

• KOL Token Mentions: Tokens mentioned by crypto KOLs (≥5 mentions) daily at 12:00 PM (noon).
• Market Data: Token and AI agent trends from sentient.market and cookie.fun daily at 2:00 PM.
• Replies: Responds to @-mentions about Solana tokens with basic analysis (planned).

Built for collaboration, this repo integrates Python (ElizaOS) for Twitter interactions and TypeScript for market data scraping and Solana analysis.

---

Features

KOL Token Mentions

• Tracks tweets from a predefined list of crypto KOLs.
• Posts the most-mentioned token (if ≥5 mentions) with sentiment analysis at noon daily.

Market Tracking

• Scrapes token prices from sentient.market and AI agent mindshare from cookie.fun.
• Posts a market update (e.g., top token by price) at 2 PM daily.

Mention Replies

• Responds to @-mentions with basic Solana token data (e.g., supply) via TypeScript analysis (planned).

---

Prerequisites

Ensure the following tools are installed with these specific versions (or later, if compatible):

• WSL (Ubuntu recommended) on Windows.
• Node.js: v20.18.3
• npm: v10.8.2 (comes with Node.js)
• pnpm: v9.15.0
• Python: v3.12.3 (or compatible version in virtual environment)
• Git: v2.39.2 (or later)
• Twitter API Keys (create an app at developer.x.com)

Setup Instructions for Developers

1. Install System Prerequisites (Ubuntu WSL)

sudo apt update
sudo apt install -y build-essential libcairo2-dev libpango1.0-dev libjpeg-dev libgif-dev libpng-dev python3-dev g++ python3 python3-pip python3-venv git
sudo ln -s /usr/bin/python3 /usr/bin/python
curl -fsSL https://deb.nodesource.com/setup_20.x | sudo -E bash -
sudo apt-get install -y nodejs
sudo npm install -g pnpm

2. Start Eliza

# Clone the repository
git clone https://github.com/elizaos/eliza.git

pnpm i
pnpm build
pnpm start

# The project iterates fast, sometimes you need to clean the project if you are coming back to the project
pnpm clean

# interact via browser
pnpm start:client

---

Roadmap

ElizaOS AI Agent: Single-agent, multi-actions, Python-based, integrated with a TypeScript agent.
Team Responsibilities: Mandes (Phase 1 & 3), Zhou (Phase 2)

---

Phase 1: Environment Setup

• Assigned: Mandes
• Tasks:
  • Environment setup ->
  • elizaOs env, connect to twitter, set AI model
  • set up Ts Token agent for data analysis
• Steps:
  1. Clone https://github.com/ai16z/eliza into eliza/, install dependencies.
  2. Configure Twitter API in eliza/.env.
  3. Initialize token-agent/ with TypeScript, @solana/web3.js, etc.
  4. Create eliza/output/ for data handoff.

---

Phase 2: Build Twitter Agent (Post)

• Assigned: Zhou
• Function:
  • Read KOL post and find out the highlight Token
  • Auto posting for x times of mentions (text & img)
  • Set character (funny, professional, present using data)
• Setup:
  • pip install tweepy vaderSentiment (for track Twitter KOL post)
• Steps:
  1. Create posting action for agent (post_kol_mentions.py)
  2. Configure Character
  3. Test
• Dependencies:
  • @0glabs/[email protected]
  • @coinbase/[email protected]
  • @deepgram/[email protected]
  • @elizaos-plugins/adapter-sqlite@<version> (linked: packages/adapter-sqlite)
  • @injectivelabs/[email protected]
  • @vitest/[email protected]
  • [email protected]
  • [email protected]
  • [email protected]
  • [email protected]
  • [email protected]
  • [email protected]
  • [email protected]
  • [email protected]
  • [email protected]
  • [email protected]
• Dev Dependencies:
  • @biomejs/[email protected]
  • @commitlint/[email protected]
  • @commitlint/[email protected]
  • @types/[email protected]
  • cli@<version> (linked: packages/cli)
  • [email protected]
  • [email protected]
  • [email protected]
  • [email protected]
  • [email protected]
  • [email protected]
  • [email protected]
  • [email protected]
  • [email protected]
  • [email protected]
  • [email protected]
  • [email protected]
  • [email protected]

---

Phase 3: Build Market Tracking Agent

• Assigned: Mandes
• Data Sources:
  • CCXT, https://docs.ccxt.com/
  • Binance, https://binance-docs.github.io/apidocs/spot/en/
• Function:
  • Get data from source, like maketcap, token price, trends, AI Agent mind share
  • Analyze data
• Steps:
  1. Find API doc of those webs
  2. Create posting action for agent (marketAgent.ts)
  3. Integrate with elizaOs
  4. Update character config
  5. Test
• Dependencies:
  • @solana/[email protected]
  • [email protected]
  • [email protected]
  • [email protected]
  • [email protected]
  • [email protected]
  • [email protected]
  • [email protected]
• Dev Dependencies:
  • @types/[email protected]
  • [email protected]

---

To Be Confirmed

Phase 4: Build Twitter Agent (Reply)

• Function:
  • Reply those mentions on Twitter
  • Update character to limit the reply topics

Phase 5: Test and Finalize

Phase 6 (Future): Build Solana Token Agent

• Function:
  • Get Token data mentioned by KOL and analyze

---