# AlphaLab

> AlphaLab is the AI quant lab you hire and direct. You bring a trading idea, a rule-based strategy, or a research hypothesis, and direct a full research team (Head of Research, researchers, an independent Risk Analyst, trader, monitor) on a desk that is already built: licensed and aligned data across stocks, futures, forex, options, prediction markets and crypto plus news and fundamentals, a deterministic backtesting engine, and the full methods bench. It supports everything from straightforward rule-based systematic strategies to advanced quantitative and ML research. Hypothesis in, defended strategy out. Access is currently by invitation via a waitlist.

AlphaLab lets a human or an AI agent build a trading strategy as a visual graph of transformation components, run backtests against real market data (stocks, futures, forex, options, prediction markets, crypto), optimize parameters, and validate out-of-sample. Agents connect over the Model Context Protocol (MCP) and drive the same capabilities a human uses in the browser.

## For agents

- MCP endpoint: https://api.alphalab.ai/mcp
- Auth: HTTP bearer token (an AlphaLab account JWT).
- Canonical workflow: search_instruments -> get_component_contracts -> validate_execution_request -> push_request -> get_execution_result.
- Capacity: a desk has a fixed research capacity per cycle. get_remaining_capacity reports how much is left; push_request refuses with capacity_exhausted when there is none.

## Pricing

The lab is hired by the month, through two doors, firms first. Every plan ships the same staff, the same built desk and the same independent Risk Analyst sign-off; the number of researchers is what changes. There is no free plan.

Firms, engaged through contracts, multi-seat with attribution and sign-off records, weekly status and a monthly review:

This is contracted rather than checked out, so it carries no list price: the researcher count and the terms are agreed with the firm.

- Firm Desk: 1 to 5 researchers, each sized for a firm's cadence, so 1 to 5 hypotheses investigated in parallel. At five, a full backlog running at once. There is no menu of firm plans: where a firm lands in that range is scoped in the engagement.
- Free Pilot: free. One scoped investigation, about thirty days, through the full process to a defended strategy or an honest refutation. How a firm engagement starts.
- Lab Setup: a fixed term, the first three to six months. For firms and family offices with capital and theses but no quant capability yet: we stand the desk up, turn the implicit rules of the book into a hypothesis backlog, and graduate a designated person onto a desk they run themselves.
- Profit share: by agreement, in place of or alongside a retainer. Proprietary firms trading their own capital only.

Self-serve, one named person directing one researcher:

- Your Desk: $990/mo, 1 researcher, 1 seat. The professional proving the lab on their own book, or a firm proving it on one account before terms.

A small number of pilots and Lab Setup programs run at a time. Contact tarek@alphalab.ai.

All plans include unlimited strategies, the full methods bench, MCP API access, paper deployment with a forward track record, and live deployment on the customer's explicit authorization.

## Docs

- [Agent quickstart](https://www.alphalab.ai/docs): connect over MCP, auth, tool inventory, and plans.
- [Concepts](https://www.alphalab.ai/concepts): canvas, components, contracts, execution styles, researchers vs seats.
- [Machine-readable summary](https://www.alphalab.ai/llms-full.txt): the full version of this document.

## Company

AlphaLab is a product by Edgebot (https://www.edgebot.com).