A multi-agent crypto trading arena where AI agents compete against each other, trading with live crypto market data from Coinbase or Binance. Each agent consumes a livestream of ticker data and standard candlestick charts, has access to its portfolio and calculator, and executes trades autonomously. This is all built with Calfkit agents, namely for their multi-agent orchestration and realtime data streaming functionality.
If you find this project interesting or useful, please consider:
â Starring the repository â it helps others discover it!
Each box (or node) is an independent process communicating with eachother. Each node can run on the same machine, on separate servers, or across different cloud regions.
Key design points:
Per-agent model selection: Each agent embeds its own model client, so different agents can use different LLMs with different providers.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Docker installed and running (in order to run a kafka broker)
An API key (and optionally base url) for your LLM provider
1. Install uv
If you don't have uv installed:
# macOS / Linux
curl -LsSf https://astral.sh/uv/install.sh | sh
# Windows
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
# Or via Homebrew
brew install uv
After installation, restart your terminal.
2. Install the Calfkit SDK
uv add calfkit@latest
Calfkit is the event-stream SDK that powers this project. It handles the agent realtime stream consumption and orechestration.
3. Start the Broker
The broker orchestrates all nodes and enables realtime data streaming between all components.
Run the following to clone the calfkit-broker repo and start a local Kafka broker container:
git clone https://github.com/calf-ai/calfkit-broker && cd calfkit-broker && make dev-up
Once the broker is ready, open a new terminal tab to continue with the quickstart. The default broker address is localhost:9092.
There's also a cloud broker version so you can simply use the cloud broker URL (which would be provided to you) to deploy your agents instead of setting up and maintaining a broker locally.
Quickstart
Install dependencies:
uv sync
Then launch each component in its own terminal. All components will access the same broker.
1. Start the exchange connector
Start either the Coinbase or Binance connector to stream live market data:
Optional: You can use the --min-interval <seconds> flag which controls how often agents are fed market data (default: 60s). Note that candle data is only updated every 60 seconds due to Coinbase API restrictions, so intervals below a minute mean agents will receive updated live pricing (bid/ask spread, ~5s granularity) but the same candle data.
2. Deploy tools & dashboard
uv run python -m deploy.tools_and_dashboard --bootstrap-servers <broker-url>
3. Deploy agents
Deploy an agent with an embedded model client and a trading strategy. Each agent runs its own LLM inference. See arena/strategies.py for the full system prompts.
For full CLI flags, config-based deployment options, and the config schema, see CLI_REFERENCE.md.
Available Agent Tools
| Tool | Description |
|------|-------------|
| execute_trade | Buy or sell a crypto product at the current market price |
| get_portfolio | View cash, open positions, cost basis, P&L, and average time held |
| calculator | Evaluate math expressions for position sizing, P&L calculations, etc. |
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
