OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Trading & Crypto Agents

Crypto Trading Arena

Crypto Trading Arena is an open-source Python system that connects AI trading agents to Coinbase or Binance market data and shared portfolio, calculator and trading tools.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Crypto Trading Arena — OpenViST project profile in Trading & Crypto Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want to assemble and observe multiple model-driven trading agents against live Coinbase or Binance market data, and are prepared to run the broker and project components yourself.

Who it is for

  • Developers building or studying multi-agent trading systems
  • Researchers or builders comparing agent strategies using a shared market feed and dashboard
  • Python users integrating model providers with event-driven agents through calfkit

Documented uses

  • Run multiple agents that respond to ticker and candlestick updates.
  • Give each agent portfolio and calculator tools for autonomous trading decisions.
  • View shared market prices and agent trading activity in a dashboard.
  • Configure an agent with a model, strategy and provider credentials.
Before you choose

Requirements & limits

The repository is public and licensed under Apache-2.0. Running the documented setup requires an LLM provider API key; a local broker setup requires Docker, while the README also describes a Calfkit cloud broker option.

  • Coinbase is the default exchange connector; Binance support is labeled experimental.
  • The architecture uses a shared Kafka-style broker for event streaming between the connector, tools and agents.
  • Each agent performs its own LLM inference, allowing different model clients across agents.
  • The README describes paper wallets and simulated fills; a distinct simulated-execution mode is identified as requiring modification.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the arena and launch its components

Install the project, connect it to a broker, and start the market feed, dashboard and an agent.

Before you start

  • Python 3.10 or later and uv
  • Docker for the local Kafka broker, or a Calfkit cloud broker URL
  • An API key for an LLM provider

Steps

  1. Clone the repository and run the command below to install dependencies.

    Documented command
    uv sync

  2. Copy .env.example to .env and set the LLM provider API key.

  3. Start a local broker using the documented calfkit-broker setup, or use a Calfkit cloud broker URL.

  4. In separate terminals, start the Coinbase connector, the tools-and-dashboard process, and an agent configured with a unique name, model ID and strategy; point each component to the same broker.

Expected outcome

The components share market updates through the broker, and deployed agents can act on the feed using trading tools; trades are reflected in the dashboard.

Guide limitations

  • The Binance connector is marked experimental.
  • Candlesticks update every 60 seconds; more frequent feed intervals provide newer live pricing but may repeat the same candle data.
  • The README documents paper wallets and simulated fills; it does not document a separate simulated-execution mode.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
8 October 2026
Original website title
ryan-yuuu/crypto-trading-arena · Official homepage title · retained in its source language
How we review sourcesSuggest a correction