Neural Inverse Cloud

Neural Inverse Cloud is the managed platform for running Neural Inverse workspaces. It pairs the Apache-licensed IDE with cloud infrastructure - persistent development environments, automatic code sync, a shared model gateway, and on-demand hardware simulation.

What's Included

Service	What it does
Workspaces	Persistent browser-based dev environments - VS Code + terminal in the cloud
Base	Git code storage - every workspace auto-syncs to a private repo
Model Gateway	Free OSS models (DeepSeek, Llama, Mistral, Kimi) - no keys required. Add your own key for Claude, GPT-4o, Gemini.
Hardware Runner	On-demand Renode simulation sessions for embedded development
Billing	Usage tracking and pay-as-you-go charging

Getting Started

Sign in at cloud.neuralinverse.com
Create a workspace from the Neural Inverse O1 template
The workspace opens Neural Inverse in your browser - fully configured, no local install needed
Your code auto-saves to Base on stop and restores on start

Architecture

Each workspace is a Kubernetes pod running the Neural Inverse IDE server. Workspaces are isolated by namespace and owner. The IDE server connects to the Cloud API for agent tokens, model routing, and hardware session management.

browser -> cloud.neuralinverse.com -> workspace pod (VS Code server)
                                   -> base.neuralinverse.com (git sync)
                                   -> free.neuralinverse.com (free OSS models)
                                   -> model.neuralinverse.com (paid models)
                                   -> run.neuralinverse.com (Renode)

Free Tier

Every account starts with:

$1.22 free credit - no payment required, use it for workspaces and hardware sessions
Free OSS models via the Model Gateway - DeepSeek, Llama, Mistral, Kimi, and more - no API key needed
Unlimited Base code storage (private repos)

After the free trial credit runs out, a $1 non-refundable hold activates pay-as-you-go billing and grants $10 free credit every month.

Self-Hosting

Neural Inverse Cloud is open-source under AGPL. You can run the full Cloud platform on your own infrastructure - workspaces, Base, and the model gateway - keeping all data in your own environment.

helm repo add neuralinverse https://charts.neuralinverse.com
helm install neuralinverse-cloud neuralinverse/cloud \
  --namespace ni-cloud \
  --create-namespace

Workspaces - create and manage workspaces
Base - code storage, SSH, registry
Model Gateway - free models and API keys
Hardware Runner - Renode simulation sessions
Billing - pricing and usage

Was this page helpful?