Your agent.
Connected to
the market.
A trading terminal for the AI you already use. Read market data, write Python strategies, backtest ideas, and prepare live execution through one CLI.
Bring your agent.
Keep your workflow.
Start with a tool that can run terminal commands. Give it access to your Marketlab installation, its documentation, and the task you want done.
These are examples of agents and tools in the ecosystem, not certified Marketlab integrations. Access depends on shell tools, permissions, and the host environment. End-to-end workflows have not been verified for every tool.
Open Codex.
Give it the prompt.
This prompt asks your agent to install or check Marketlab, confirm its runtime, and report back before configuring trading.
Open Codex Marketlab installation guideI am using Codex.
# Set Up Market Lab
Install or upgrade Market Lab on this machine and verify the setup.
Official documentation:
https://docs.marketlab.sh/
Read the Installation and Daemon pages before acting. Use the docs and the installed CLI's `--help` output as the source of truth.
1. Inspect the operating system, architecture, `PATH`, and any existing `mlab` installation.
2. Ask whether `mlabd` should use the **Native** or **Docker** backend. Do not choose or change the backend silently.
3. Follow the documented install or upgrade flow.
4. Verify:
```bash
mlab --version
mlab daemon backend
mlab daemon status
```
Ask before configuring market data, authentication, execution, SSH transport, or Python.
Never ask the user to paste a private key or API key into chat. Keep authentication inside Market Lab's hidden terminal prompts. Never place a live order during setup; use `--dry-run` when a check requires an execution plan.
Finish with the installed version, selected backend, daemon status, any optional setup completed, and one safe next command.
From an idea.
To a running strategy.
Your agent works through the CLI. Marketlab supplies the data, backtesting, execution commands, and job state.
- 01
Research the market
Ask your agent to discover markets, inspect order books, and investigate a trading idea.
mlab markets --exchange hyperliquid --hip 1 - 02
Build and backtest
Have it write a plain Python strategy, run a backtest, and explain the assumptions and results.
mlab script backtest --help - 03
Review and deploy
Review the execution plan. Authorize live activity explicitly, then deploy the configured strategy.
mlab script run --help - 04
Inspect and adapt
Read job state, examine logs, and stop or revise the strategy as needed.
mlab script jobs
Your agent reasons.
Marketlab runs.
The agent can inspect results, change code, and decide what to do next. A deployed strategy runs in Marketlab’s daemon and can continue after the deploying terminal closes.
Ongoing AI decisions require a running agent harness. The host, daemon, network, and venue must remain available for execution.
“Use Marketlab to inspect the available BTC market data, build a simple Python strategy, and backtest it. Explain the assumptions and results. Prepare a deployment plan for my review.”Explore Python strategies
Give your agent
its first market.
Get the setup prompt Third-party names and logos identify their respective tools. No affiliation or endorsement is implied.