# SimForge > SimForge is a driving simulator for autonomous-vehicle research: scenarios in SimForge Worlds (real-world HD maps with their digital twins), closed-loop simulation with reactive traffic, 2D, schematic and photoreal 3D sensor rendering with the Helios Engine, Recast (a recorded drive turned into an editable scenario), and SimForge Gym, where you train driving policies (reinforcement learning today, supervised fine-tuning recipes coming). One command line, `simforge`, runs everything on your machine, or on SimForge's hosted cloud with `--cloud`. - The `simforge` CLI and SimForge Gym (the `simforge-gym` Python package) are Apache-2.0. The runtime they drive (simulation engine and renderer) is a closed binary under the PolyForm Noncommercial License 1.0.0; downloading it and the SimForge Worlds maps requires signing in and accepting the SimForge account and download terms, which make usage telemetry a condition of SimForge's services and license the maps for non-commercial use without redistribution. - Every command prints one JSON document on stdout, and a failure prints `{code, path?, reason, hint, detail?}` on stderr. Exit 0 is ok, 1 means the command could not run, 2 means it ran and found something wrong with its input. - `simforge --help --json` prints the whole command surface. Never guess a flag. - Linux x86_64 only. Training with SimForge Gym runs locally; the cloud runs renders, simulations, Recast log ingestion and transfers, and `simforge datasets pull` downloads hosted datasets as files. ## Get started - [SimForge docs](https://simforge.mintlify.app/index.md): Install the simforge CLI, download the runtime and a map, render a scenario in 2D, schematic or 3D, train a policy with reinforcement learning, and run the same commands in the cloud. - [Quickstart](https://simforge.mintlify.app/quickstart.md): From nothing to a rendered scenario - install the CLI, sign in, render on SimForge cloud with no GPU, then install the runtime and a map to render locally in 3D and 2D. - [Install the CLI](https://simforge.mintlify.app/install.md): Install the simforge command line on Linux, macOS or Windows and check the machine with simforge doctor. - [Sign in and install the runtime](https://simforge.mintlify.app/sign-in.md): Sign in with simforge login, accept the runtime's PolyForm Noncommercial license and SimForge's account and download terms, and install the closed runtime that simulates and renders. ## Guides - [SimForge Worlds and assets](https://simforge.mintlify.app/maps.md): Download SimForge Worlds (the public maps) with simforge maps pull, fetch the actor models, and manage the local cache. - [Author a scenario](https://simforge.mintlify.app/scenarios.md): Create a scenario on an installed map and change it with typed, atomic authoring operations instead of editing JSON by hand. - [Preview and render](https://simforge.mintlify.app/render.md): Render a scenario as a 2D top-down video, a schematic view or photoreal 3D sensor data, on your machine or in the cloud. - [Train with SimForge Gym](https://simforge.mintlify.app/gym.md): Train driving models with SimForge Gym (the open simforge-gym package) on your own machine. Three recipes, one command each: a starter that fine-tunes Qwen Drive on four scenarios, supervised fine-tuning of Qwen Drive and Alpamayo 1.5, and reinforcement learning with PPO and closed-loop GRPO. - [Run in the cloud](https://simforge.mintlify.app/cloud.md): Run the same simforge commands on SimForge's machines with --cloud, price them with --dry-run, cap them with --max-cost, and download the results. - [Getting data out](https://simforge.mintlify.app/datasets.md): Pull a hosted dataset, a filter of it or chosen scenarios as files with the CLI, an agent, a link list or the API; resumable, checked and verifiable offline. ## Sensors - [Custom sensor rigs](https://simforge.mintlify.app/sensors.md): Bring your own cameras, lidar and radar: the rig file, the vehicle frame and rotation conventions, render profiles, and how to use one rig locally, in the cloud and across scenarios. - [Rig file reference](https://simforge.mintlify.app/sensor-reference.md): Every field of a simforge.render-rig/v1 sensor rig, with its type, range, default and units, and what the renderer supports on top. - [Example rigs](https://simforge.mintlify.app/sensor-examples.md): Three complete sensor rigs, each rendered end to end on a public map - a front camera, a seven-camera surround rig, and a camera with lidar and radar. - [Sensor outputs](https://simforge.mintlify.app/sensor-outputs.md): What a render writes for each camera, lidar and radar - the folder layout, file formats, timestamps, the camera and vehicle poses - and how to load it in Python. - [Sensor performance and troubleshooting](https://simforge.mintlify.app/sensor-troubleshooting.md): How sensor count, resolution and passes change render time, GPU memory and cloud price; the limits; and the rig errors you can hit, with their fixes. - [Sensor rig JSON Schema](https://simforge.ai/docs/render-rig.schema.json): `simforge.render-rig/v1`, the file `simforge render --rig` reads and `simforge rig validate` checks. ## Reference - [JSON output, errors and exit codes](https://simforge.mintlify.app/output.md): The contract every simforge command keeps - one JSON document on stdout, a structured error on stderr, and exit codes 0, 1 and 2 - so scripts and agents can rely on it. - [Usage telemetry](https://simforge.mintlify.app/telemetry.md): What the SimForge runtime reports about how it is used, what it never collects, and how to see the data before it is sent. - [Command reference](https://simforge.mintlify.app/cli/index.md): every `simforge` command, argument and flag (CLI 0.2.0-rc.5), generated from the CLI. - [CLI surface JSON](https://simforge.ai/docs/cli.json): the same reference as `simforge.cli-surface/v1` JSON, exactly what `simforge --help --json` prints. - [Cloud API OpenAPI](https://simforge.ai/docs/openapi.json): the hosted API (`/api/v1`) that `--cloud` uses. ## For agents - [For AI agents](https://simforge.mintlify.app/agents.md): Where an AI agent finds the SimForge docs, the machine-readable command surface and API, and the skills pack, and how to drive the CLI safely. - [Agent skills pack](https://simforge.mintlify.app/skills.md): Install the SimForge agent skills into Claude Code, Codex or any agent that reads AGENTS.md, from the CLI or as a zip download. - [Skills pack (zip)](https://simforge.ai/docs/simforge-skills.zip): the SimForge agent skills for Claude Code, Codex and AGENTS.md agents. - [Agent sign-in (auth.md)](https://simforge.ai/auth.md): how an agent signs in to the hosted API for a person, without the CLI: register with their email, they approve with a code, then call `/api/v1`. ## Optional - [Everything in one file](https://simforge.ai/llms-full.txt): every page above and the command reference.