# tradefloor > A reproducible evaluation environment for financial AI agents. A > deterministic market simulator with order-book execution, macro dynamics, > causal ground truth and agent-native interfaces. Version 0.8.7. Run controlled, reproducible experiments on trading agents in a market with realistic execution, rather than backtesting them over historical prices. The same universe, macro state and seed produce the same market on every supported platform, so a result can be re-run by anyone who has those three. Four properties these pages document and measure: - reproducible: the same seed gives the same market on Linux, macOS and Windows - execution-aware: agents trade through an order book and pay their own impact - inspectable: eleven factor contributions sum to each price move, residual ~1e-16 - agent-native: a Python object, a Gymnasium environment, a model over MCP, or an agent from the OpenAI Agents SDK, PydanticAI, LangGraph or FinRobot What it does not do is predict real markets. The realism envelope states what has been measured, over what horizon and on what configuration, and names five gaps that each end in a rule about what the simulator must not be used for. When quoting this project, cite the preset and the version, not "tradefloor": every preset is frozen and named, and the numbers change between them. The product site is https://tradefloor.dev/. ## Front door - [Quickstart](https://docs.tradefloor.dev/): Install tradefloor, run a five-company market for 20 days, score a simple trading agent on it and read its scorecard, in one script you can download. ## Getting started - [Quickstart](https://docs.tradefloor.dev/): Install tradefloor, run a five-company market for 20 days, score a simple trading agent on it and read its scorecard, in one script you can download. - [Install](https://docs.tradefloor.dev/install.html): Install tradefloor with pip, check the version and default preset, and add the optional extras for MCP, Gymnasium, Arrow tables and LLM agent frameworks. - [Reproducibility](https://docs.tradefloor.dev/reproducibility.html): What fixes a tradefloor market, what an untraded and a traded run promise across platforms and releases, and what a preset name does and does not pin. - [Troubleshooting](https://docs.tradefloor.dev/troubleshooting.html): Fixes for install errors, missing extras, agents that never trade, refused orders, shares sent as weights, missing history, replay errors and model failures. - [Glossary](https://docs.tradefloor.dev/glossary.html): Short definitions of the terms the tradefloor documentation uses, from preset, seed and universe to decision step, tick, fork, manifest and fair value. ## Guides - [Write an agent](https://docs.tradefloor.dev/guide-agent.html): Write a trading agent for tradefloor: the act(obs) method, the orders it returns, sizing to a target weight, what the agent can see and warm-up history. - [Compare strategies](https://docs.tradefloor.dev/guide-compare.html): Compare trading agents in tradefloor: against buy-and-hold on one market, across many seeds with rank and a paired sign test, and by what their trades cost. - [Fork a market](https://docs.tradefloor.dev/guide-fork.html): Fork a tradefloor market to run two futures from one past: checkpoints, engine branches, and a counterfactual that runs one agent under a scenario and without it. - [Record and replay](https://docs.tradefloor.dev/guide-replay.html): Record an LLM agent's answers in tradefloor and replay the run without the model: transcripts, what a replay checks, saving a recording and a manifest of the market. - [LLM adapters](https://docs.tradefloor.dev/llm-adapters.html): Run an LLM agent inside a tradefloor market on your machine with the OpenAI Agents SDK, PydanticAI, LangGraph, FinRobot or a function: setup, a first run, fixes. - [Local MCP server](https://docs.tradefloor.dev/mcp-local.html): Run tradefloor's MCP server on your machine so an MCP client can build markets, score strategy specs and explain price moves. It places no orders. - [Hosted app](https://docs.tradefloor.dev/hosted.html): Connect an agent or a bot to hosted markets on app.tradefloor.dev, in beta: MCP at /mcp, the HTTP API at /v1 and an Alpaca-shaped API. Hosted tools place orders. ## API reference - [API index](https://docs.tradefloor.dev/api.html): tradefloor's public APIs, grouped by task, with a complete alphabetical index of every supported public symbol and the page that documents it. - [Engine and data](https://docs.tradefloor.dev/core-types.html): Run a market and read what it made: Engine, Universe and Macro, the Arrow output tables, real companies from EDGAR, units, and every typed member. - [Agents and evaluation](https://docs.tradefloor.dev/evaluate.html): Reference for tradefloor agents: what act returns, what an agent can see, and evaluate, rank, tca.analyse, Scorecard, Ranking, AgentRecord and RunManifest. - [Forks and counterfactuals](https://docs.tradefloor.dev/api-counterfactual.html): Fork a market, checkpoint it and run one agent in two worlds that differ in one input: Checkpoint, branch, World, agree and compare, with usage first. - [Scenarios](https://docs.tradefloor.dev/api-scenario.html): Apply a shipped scenario or write your own: the seven scenarios, the fifteen targets, the command line, then the Scenario and Intervention reference. - [LLM adapters and MCP](https://docs.tradefloor.dev/api-integrations.html): Run an agent from LangGraph, the OpenAI Agents SDK, PydanticAI, FinRobot or a plain function, record and replay it, and use the MCP server's tools. - [Gym environment](https://docs.tradefloor.dev/rl-environment.html): A Gymnasium environment where a policy's own orders move prices, so it pays for the size it trades. Actions are target weights and reward includes the impact. - [Model parameters](https://docs.tradefloor.dev/parameters.html): Reference for ModelParams and every entry it exposes: the settable names, their types, their values under the shipped preset, and what each one controls. ## Model and validation - [How prices are made](https://docs.tradefloor.dev/how-prices-are-made.html): The mechanism behind every simulated price: fair value from earnings and rates, a mispricing that reverts, volatility read off the VIX, and an order book. - [Why pt-v20](https://docs.tradefloor.dev/why-pt-v20.html): What the default model gets right about crashes, rates, earnings and trading costs, why that matters when you test a strategy or an agent, and its limits. - [How it is measured](https://docs.tradefloor.dev/how-its-measured.html): How the default model is graded: checks registered before the run, exam seeds the tuning never saw, 40 rows over 21 years, the one-year table, the grade. ## Releases - [Release notes](https://docs.tradefloor.dev/release-notes.html): Every release and what it changed. An untraded run that names its preset replays exactly under later versions, and one that took the default does not. - [Support policy](https://docs.tradefloor.dev/support.html): Which tradefloor releases get fixes and for how long, what a patch release may change, how presets are frozen, and the digests each release checks. - [Citing tradefloor](https://docs.tradefloor.dev/cite.html): How to cite tradefloor in a paper: the BibTeX entry, the version and preset to name, and what to publish beside a result so a reader can rebuild the market.