Your own GPU workstations and build servers sit idle most of the time. The awaBerry Agentic API turns any registered device into an authenticated HTTP endpoint — callable from any script, CI pipeline, or application, with zero open ports.
Your own machines — GPU workstations, build servers, home rack servers — sit idle most of the time. Yet when you need their power remotely, your options are clunky: rent expensive cloud GPUs, open SSH ports to the internet, set up VPN tunnels, or build and maintain a custom REST wrapper yourself. Each approach carries real costs: credential sprawl, key rotation, cold-start latency, data egress fees, or significant maintenance overhead.
SSH keys need rotation. VPNs need maintenance. Custom REST wrappers take weeks to build correctly. None of these are designed for on-demand, scriptable compute access.
Cloud GPU instances bill by the second and add egress fees for large datasets. Your own hardware is more cost-effective — but only if you can actually reach it cleanly.
awaBerry Anywhere provides a zero-trust tunneling layer that sits in front of your physical devices and exposes them as authenticated HTTP endpoints. No firewall ports opened, no SSH keys managed, no custom middleware built. The API handles authentication, permission scoping, and secure tunneling automatically — turning your idle hardware into callable compute nodes accessible from anywhere.
Assign the target device to an Agentic API project. Define the command allowlist (specific scripts only), scoped folder paths, and privilege level. Retrieve your Project Key and Secret.
Any script, CI pipeline, or application sends a POST to /api/v1/execute with your command and device identifier, authenticated via Bearer PROJECT_KEY:SECRET. No SDK required.
Receive stdout, stderr, and exit_code in the JSON response. Chain calls across machines for multi-step compute pipelines — no inter-machine credentials needed.
Once a project is configured, your hardware is available for any programmatic use case:
POST a command to run your inference script on a dedicated GPU machine. Receive the structured prediction result back in the response body — no cloud GPU required.
A GitHub Actions or Cloudflare Workers CI job triggers a private build machine via the Agentic API. Collect stdout for build status, exit code for pass/fail gating.
Replace fragile cron setups with API-triggered processes orchestrated from a Cloudflare Worker. Full observability (exit codes, stdout, stderr) without managing cron infrastructure.
Chain calls across machines: preprocess on Machine A, run inference on GPU Machine B, post-process on Machine C. No inter-machine credentials or VPN needed.
| Setting | Recommended Value |
|---|---|
| Programmatic access | ✅ Enabled |
| Administrator permissions | ❌ Only if root is explicitly required |
| Folder access | Scoped to project-specific directories only |
| Command execution | Allowlist specific scripts — no open shell |
| Number of devices | One per compute role for isolation |
Access your Raspberry Pi, NAS, or home server from anywhere — no DDNS, no port forwarding, no VPN configuration. Install the agent and your hardware becomes a clean authenticated endpoint.
Replace SFTP and S3 bucket ACLs with zero-trust scoped folder access. Each partner or CI pipeline gets a Project Key scoped to exactly one directory — instantly revocable, no open ports.
awaBerry Anywhere is a zero-trust remote access platform that gets any device — cloud server, laptop, or SoC hardware — securely accessible from anywhere in minutes. No VPNs, no open inbound ports, no complex configuration or additional remote connection software. Works on any MAC - yes even an old Apple macbook from 2012. Works on any Ubuntu / Debian / Redhad based LINUX. Works on any Windows which supports the Windows Subsystem for Linux (WSL).
Flexible onboarding for any hardware — in any environment.
Full control and activation via the awaBerry web dashboard.
awaBerry Automation is the combination of two tightly integrated products that together form a complete, AI-native automation platform.
Uses the Google Gemini CLI to translate plain-English instructions into executable scripts — run on your local devices on a schedule. AI tokens are spent exactly once to generate the logic; every subsequent execution costs nothing.
Read more →Secure, zero-trust device access as-a-service. Exposes your registered devices to programmatic access via encrypted tunnels — grant AI agents, scripts, or collaborators precisely scoped access.
Read more →Fundamentally different: a complete, AI-native automation platform — across every device you own, anywhere in the world.
Read more →Automate operations, manage fleets, and enable secure remote work for your entire team.
Access your home devices, automate personal tasks, and share access with family — for free.
Access lab hardware, automate data collection, and collaborate across institutions.
The only thing missing was a secure, zero-friction way to call it remotely.