Docs menu

// Get started

Quickstart

From nothing to rendered frames on your own Linux machine - install the CLI, sign in, install the runtime and a map, and render a scenario in 3D and 2D.

View as Markdown

This takes you from an empty machine to camera frames, instance-id, depth and semantic passes, and a video, rendered locally. Check what the machine needs first: Linux x86_64 (Ubuntu 24.04 or later), an Apple silicon Mac or Windows x64; for 3D an NVIDIA GPU with at least 8 GiB, or Apple M3 or newer. In Docker, start the container with the NVIDIA runtime's graphics capability (Running in Docker); plain --gpus all cannot start Vulkan.

1. Install the CLI#

sh
curl -fsSL https://simforge.ai/install.sh | sh

2. Sign in, accept the agreement, install the runtime#

sh
simforge login --device                    # prints a URL and a code; approve it in your browser
simforge runtime license                   # read the agreement; nothing is accepted yet
simforge runtime install --accept-license  # accepts that exact version, then downloads the runtime
simforge doctor                            # what is installed, and the fix for anything missing

Accepting the agreement is what entitles your account to the runtime and the maps. Every download is signed by SimForge: the CLI checks the signature and the sha256 of each archive before it installs anything.

3. A scenario and its map#

sh
simforge maps pull easterbrook-discovery-school --accept-license
simforge scenario new --map easterbrook-discovery-school --out s.json

Then add actors with typed authoring operations. A scenario from the SIMLOG-25k dataset works the same way: download its whole folder and pull the map it names.

The SIMLOG-25k dataset is on Hugging Face: huggingface.co/datasets/SIMFORGE-AI/simlog-25k.

4. Render#

sh
simforge render s.json --mode 3d --out frames        # photoreal, one front camera
simforge render s.json --mode 2d --out topdown       # top-down video, no GPU needed

The 3D render uses one front camera on the ego: 1280x720 at 24 fps, the showcase preset, locally and with --cloud. Preview and render covers other rigs, presets, texture tiers and the output format; add --cloud --max-cost <cents> to render the same scenario on SimForge's GPUs instead.