Skip to content

Repository files navigation

Avantis Trading Skill — Surfin (Call Your Quant)

Surfin agent (e.g. Surfin' Alpha) for agentic trading on Avantis (Base perpetuals) using the Avantis Trader SDK. Logic is aligned with Call Your Quant and configured as an active Cursor skill. Strategy: simple PnL focus (SL 15–20%, sensible leverage, risk sizing).

Setup

  1. Python 3.10+ recommended.

  2. Create virtualenv and install:

    python3 -m venv .venv
    source .venv/bin/activate   # Windows: .venv\Scripts\activate
    pip install -r requirements.txt
  3. Configure environment:

    cp .env.example .env
    # Edit .env: set AVANTIS_PROVIDER_URL and AVANTIS_PRIVATE_KEY (and optionally AVANTIS_REFERRAL=SURFIN)
  4. Wallet: Ensure the wallet has USDC on Base and some ETH for gas. Minimum suggested: ~$15 USDC for first trade.

Usage

  • Cursor skill: The Avantis trading skill is in .cursor/skills/avantis-trading/. When you ask the agent to open/close positions, set TP/SL, or manage Avantis trades, it will use this skill and the SDK.
  • Avantis (direct): python -m trading list / python -m trading open ...
  • ClawdBots Arena: Set CLAWDBOTS_API_BASE (and optional CLAWDBOTS_AGENT_NAME, etc.) in .env, then:
    python -m clawdbots register   # once: get trading_wallet, fund with ≥$10 USDC on Base
    python -m clawdbots status     # check balance and positions
    python -m clawdbots run        # heartbeat loop (keep agent active during arena)
    python -m clawdbots trade open_long ETH/USD 5 25 --reasoning "Surfin signal"
    python -m clawdbots withdraw <to_address> <amount_usdc>
    # Public GETs (no auth): arena-status, agents, realized-pnl --arena-id arena-59, thoughts
    python -m clawdbots agent-loop [--interval 60] [--dry-run]  # observe→reason→act loop
    Agentic trading: Use Cursor skill "clawdbots-arena" (observe with GETs, then decide, then trade/heartbeat). See docs/AGENTIC-ARENA-DESIGN.md and docs/ARENA-GET-ACIKLAMALAR.md.
  • Arena Telegram notifier: When arena becomes active, get a Telegram alert (e.g. run 24/7 on Railway):
    # Set TELEGRAM_BOT_TOKEN and TELEGRAM_CHAT_ID in .env, then:
    python arena_telegram_notifier.py
    Checks every 5 minutes; sends one message per arena start. See .env.example for vars.

Resources

About

No description, website, or topics provided.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages