SENTINEL
A real-time node graph built for agents, not adapted for them.
Vibe-code it. Take it apart. Put it on stage.
Free to build with. No time limit. Windows · NVIDIA.
You bring the what. It brings the how.
Years of shader math, data wrangling, engine quirks — that's its job now. Yours is the part that was always the point: knowing what it should be, and pushing it past the first version that works.
It builds the nodes and the panels to drive them.
Describe what you need and the agent writes it as real GPU shader code, made for the problem in front of it. The part fits the idea instead of the idea fitting the part. The controls come with it: the pads, scopes and mode switches that idea needs, drawn right in the viewport. Any harness drives it, including a local model, so the ceiling rises with frontier intelligence rather than with our roadmap.
Sound drives anything.
System audio or a mic, resolved into spectrum, mel bands and beat detection that can drive any parameter in the graph. Point a kick drum at a swarm and watch it scatter on the beat.
You decide what connects. It works out how.
Depth, hands, gestures, bodies, corners, blobs and edges, all running live off the same webcam at the same time. No Python virtual environments, no engines to build.
Each one publishes typed data on a single connection rather than a tangle you have to reshape by hand. The agent reads those types and wires the integration itself, so "relight the scene from the depth map and throw lightning off the fingertips" is a sentence instead of an afternoon of data wrangling.
Live diffusion.
Powered by Stability AI
Explore infinite worlds.
A feedback loop with depth and parallax estimation blended back in, so the frame stays coherent in three dimensions while it keeps regenerating. Steer with prompts and image references and travel as far in as you want to go.
Transform your world.
A streaming diffusion implementation rewritten from the ground up in native C++ on TensorRT, running SDXL Turbo. That rewrite is what makes it one of the fastest you can run, and why there is no Python virtual environment to repair before a show. Up to 54 fps at 896 × 512 with IP-Adapter on a 5090, upscaled 2× through a pipeline built to hold detail. ControlNet takes depth or line art so the result follows the shape of what you fed it, and you can build engines for your own models.
Nothing here was imported.
No mesh files, no textures, no asset store. Forty arms, every surface a signed distance field the agent wrote, at 60 fps on one GPU. Bring your own models when a job needs them. This needed none.
Pricing
Own your tools.
Founding price. Goes to $249.
- One-time purchase. No subscription.
- 12 months of updates and support, then $80/year if you want to keep getting new builds.
- Versions you own keep working forever.
- Activate on 2 machines.
[ ! ] ALPHA — Sentinel ships most weeks and moves fast. $199.99 gets today's app plus a year of what lands next.
Includes 12 months of updates & support · 2 machines · versions you own keep working forever
You are purchasing a revocable license to access Sentinel, not ownership of the software. This license is subject to our EULA and may be revoked in accordance with its terms.
Know when there's a new build.
Sentinel ships most weeks. Get an email when a stable release lands, and nothing else.
Questions.
01Do I need an agent?
Yes. Sentinel is built to be driven by one, and that is the point of it: you describe what you want, and the agent builds it, from the stage rig to the laser looks to the controls. Bring Claude Code, Codex, or a local model in any harness you like. The agent isn't included. If you've never used one, the quickstarts for Claude Code and Codex show how to install one on Windows and sign in.
02How does the agent work?
It runs beside the graph and talks to it over MCP. It writes HLSL shader modules and Luau scripts and wires them in. Everything it writes is readable files on your disk. There is no metered generation and no credits; you bring your own model.
03Why not just point an agent at an existing node tool?
You can, and people do. The catch is that you're driving software built for human hands, so the agent takes the long way round, and whatever it builds is still capped by the node set someone else shipped. This was built to be operated by an agent from the start. Everything is reachable by one, and the nodes it writes are real GPU code on your disk, so there's no ceiling to work around.
04What's in the free version?
Everything, with no time limit: every node, everything your agent can do, the full stage simulation with simulated lasers, MIDI, the Push 2, and Spout and NDI in at any size. Spout, NDI, and display out work too. Together they share 720p's worth of pixels, in any shape, and a display output still fills a screen of any size. A license unlocks the rest of what reaches the real world: video out above 720p, laser output, DMX beyond 1 universe out and 4 in, and recording above 1080p. Lasers, DMX, MIDI, the Push 2, and the free video out are in the nightly on the download page, and come to stable next.
05What hardware do I need?
Windows and an NVIDIA RTX 30-series GPU or newer. Shader and agent-built scenes run on ordinary RTX cards. Live diffusion is the heavy part: it needs 12 GB on a 40-series or newer, or 16 GB on a 30-series. It runs on a 12 GB laptop 5070 Ti at FP8 with IP-Adapter. Heavier pipelines want more.
06What happens after my year of updates?
Every version released before your expiry keeps working forever. Renewal will be $80 a year if you want the newer builds, and nothing stops working if you skip it. You can decide when you get there.
07What can it talk to?
Lighting over Art-Net and sACN, in and out. Lasers through Ether Dream, LaserCube, and ShowNET, or into Pangolin BEYOND, and ILDA files in and out. Timecode in as Art-Net timecode, MTC, or LTC. MIDI controllers, with native Push 2 support down to its screen. GDTF fixtures and MVR stages. OSC in and out. Spout and NDI in and out, display output, and webcams and capture cards. Video files in HAP, H.264, and H.265. Mesh import for OBJ, FBX, glTF, and GLB. Export is MP4, or a deterministic, frame-accurate PNG sequence when you need one. DMX, lasers, ILDA, timecode, MIDI, GDTF and MVR, and HAP are in the nightly on the download page, and come to stable next.
08Will it work with my lighting console?
Yes, over Art-Net or sACN, in the nightly. Sentinel can show you what your console sends, or send to your fixtures itself. The free version takes in 4 universes and sends 1, and a license raises both to 1,024.
09Does it need the internet?
Only to use an online agent like Claude Code or Codex. A show you've already built runs with no connection, models included once they're downloaded. A license needs the internet once, to activate. After that, Sentinel checks it against a file on your computer, so there's no check-in at the venue and no dongle. The free version needs no account at all.
System requirements.
| Minimum | Recommended | |
|---|---|---|
| GPU | NVIDIA RTX 30-series or newer | RTX 4090 / 5090 |
| GPU · diffusion | 40-series or newer, 12 GB · 30-series, 16 GB | RTX 4090 / 5090 |
| CPU | Intel Core i7 / AMD Ryzen 7 | Intel Core i9 / AMD Ryzen 9 |
| RAM | 16 GB | 32 GB |
| OS | Windows 10 64-bit | Windows 11 |
| CUDA | 12.x | 12.x |
Live diffusion is the only part with a real VRAM floor. Everything else, including every scene on this page, runs on much less.
Sentinel is built by one person and an agent, and it ships most weeks. Try it and help shape what it becomes.