Install NeuraFrame Studio™ on ARM64 or x86_64 Linux. Start with a 7-day free trial per device.
For Jetson Orin, ARM64 edge systems, robotics platforms, and supported ARM64 Linux devices.
SHA256: verify checksum
For Linux workstations, servers, local LLM hosts, and development systems.
SHA256: verify checksum
Do not replace your model provider. Put NeuraFrame™ in front of it. The x86_64 build runs a reuse-aware proxy in front of your provider: point your app's base URL at NeuraFrame™ and change nothing else. Repeats are served from memory; everything else is forwarded to your provider unchanged. If NeuraFrame™ has no stored answer and cannot reach your provider, it says so plainly. It never makes one up.
For applications already using OpenAI-style chat, completion, or compatible API patterns.
For applications routing Anthropic-style model requests through a server-side AI gateway.
For teams using Grok or xAI-style model access through configurable API routing.
For private, hosted, or local model endpoints that expose compatible HTTP model APIs.
Download x86_64 (Gateway) Gateway guide
Same x86_64 package, same per-device licensing. The gateway runs on 127.0.0.1:8081; set your provider as the upstream and point your app at it. See the gateway guide.
Raise it in simulation. Ship the memory. It keeps learning. Train a NeuraFrame™ instance on a server with your model, then deploy only NeuraFrame™ to the robot: no model on board, just the learned memory and the light engine. It acts on what it has learned and escalates what it has not. Why Embodied, or the technical guide.
Jetson Orin and any other ARM64 Linux board. Use it as the robot, or as the training server if that machine is ARM64. The light engine and learned memory only, no model on board.
SHA256: verify checksum
Industrial PCs, workstations, and servers. Use it as the training server, or as the robot if your robot is x86. Same light package as the ARM64 build; your heavy model and simulator run alongside it and are not part of this download.
SHA256: verify checksum
Two builds, one per processor architecture. Either can be the robot or the training server, chosen by the machine's CPU; there is no separate robot edition, and neither build contains a model. Only the memory pack travels between them.
7-day free trial per device. Per-device licensing at $25 per month or $250 per year. See Embodied pricing. Embodied is a new capability; the safety rules are a tool, not a guarantee, and you are responsible for your own model, integration, and safeguards. See the EULA.
Run the Fleet server in your own cloud or on-prem to manage curated round-trip learning across a fleet, for both Studio Fleet and Embodied Fleet. Devices learn, you approve what should spread, and it is distributed back, signed and non-destructive, with an inventor vault and provisioned device identities. How Fleet works.
Pure Python, runs on any modern x86_64 or ARM64 Linux. The fleet client already ships in the Studio and Embodied packages, so your devices can join.
SHA256: verify checksum
Studio Fleet shares verified reuse memory across servers and devices. Embodied Fleet shares learned behavior across robots. Same round trip, curated by you.
| Operating system | Linux ARM64 or x86_64 |
| Model | A local model or compatible workflow |
| Activation | Internet for online trial and license activation |
| Offline | Offline licensing available by request |
| Recommended | NVIDIA Jetson Orin or a Linux workstation for heavy local AI workloads |
Install NeuraFrame Studio™ across many machines at once and license the whole fleet from one place, with a single enrollment token.
Extract the package, run the installer, and start the trial.
# ARM64 shown; use the x86_64 package on x86 systems # optional: verify the download against its published checksum sha256sum -c neuraframe-studio-jetson-0.3.0.tar.gz.sha256 tar -xzf neuraframe-studio-jetson-0.3.0.tar.gz cd neuraframe-studio sudo bash install.sh neuraframe trial start neuraframe status