Give AI agents access to your systems without giving up control.
The SAFi Appliance is a turnkey, on-premise hardware device that combines capable local AI with strict runtime governance. It acts as a functional extension of your IT team, safely automating routine infrastructure and security operations with a complete, tamper-evident audit trail.
- Zero Cloud Liability: Your data, credentials, and IP never leave your physical network.
- Skip the Setup: Turn it on with 3 pre-loaded local reasoning models ready to run.
- An Extra Set of Hands: Sysadmin, Security & Developer agents automate scans, patching, and scripting.
- You Write the Rules: Deterministic policy guardrails enforce only what you authorize.
- Audit-Ready by Default: Every action is logged in a tamper-evident trail for compliance.
The Reality & The Unlock
Why IT Teams Are Blocked from AI, and How SAFi Solves It
IT leaders are stretched thin and want AI agents as a force multiplier for troubleshooting, hardening, and code, but four blockers keep them from giving AI access to their networks.
Why Cloud AI Is Off-Limits
- Black-Box Execution: No deterministic guardrails before commands run.
- Privacy & IP Exposure: Configs, credentials, and proprietary code leave your network.
- No Audit Trail: Missing compliance records for legal or regulatory review.
- Lock-In & Cloud Bills: Unpredictable token costs and external vendor dependency.
How SAFi Unlocks It
- You Write the Rules: Policy-enforced execution acts as a secure extension of your IT team.
- 100% On-Premise: All data and IP stay on hardware you physically control.
- Tamper-Evident Audit Trail: Every prompt, check, and action recorded locally.
- Predictable Economics: $4,500 one-time, zero cloud token bills.
Deployment & Operations
How the appliance works
The setup takes less than 15 minutes. The appliance is shipped ready for you to connect to your network and log in, with all models and agents pre-configured to work out of the box. Read the step-by-step Quick Start Guide.
Plug & Play Setup
Connect power and Ethernet. The appliance configures automatically via DHCP or a static IP, immediately serving your private web dashboard and API endpoint on your local network.
Web Browser or Terminal Access
Open the web interface from any browser on your network with zero workstation setup. For developers and sysadmins who work in the shell, the optional safi-cli utility connects your terminal directly to the appliance.
Isolated Execution Sandboxes
When running command-line tasks, tools execute inside unprivileged Linux Bubblewrap sandboxes locked strictly to your chosen project directory, with zero access to root files, SSH keys, or host credentials.
The IT Agent Triad
The Agents
The IT agents on the SAFi Appliance are not just chatbots. They operate at the command-line layer, so instead of typing commands, remembering syntax, or piecing together procedures, you state the intent and supervise the result. Each agent is governed by a policy that you author and control, and this separation of roles gives you a clean audit trail of everything each agent does.
The result is a shift in how your team works: less time spent as command-line operators, and more time directing outcomes and improving the overall system.
Use the agents from the web portal or natively in PowerShell and Terminal (Bash) with zero external connectors or MCP setup, all governed by policies you manage.
Sysadmin Engineer
Handles updates, troubleshooting, DNS and email authentication (SPF, DKIM, DMARC), and routine maintenance across Linux, Windows, and Microsoft 365 environments.
Security Engineer
Runs external and internal vulnerability assessments, audits exposed remote-access or Shadow IT surfaces, and checks server and web header hardening.
Software Engineer
Works completely locally in your repositories, writing internal scripts, refactoring applications, or converting legacy WordPress/CMS brochure sites into fast, hardened static sites.
Live Demo: Sysadmin Engineer Checking SPF, DKIM & DMARC via safi-cli
Build Custom Agents for Your Stack
The IT agents get your team working on day one, but you are never limited to just three roles. Define and deploy as many custom, role-specific agents as your workflow needs using the admin web portal.
Local Foundation Weights
Pre-Loaded Local AI Models
The appliance ships with three vetted, locally hosted reasoning models pre-loaded and ready to run: Qwen (27B) for deep security, coding, and multi-step troubleshooting, Qwen MoE (35B-A3B) for rapid scripting and documentation, and Gemma 4 (26B-A4B) for fast, structured tool execution. We continuously benchmark new open models and deliver vetted updates over time.
Zero False Refusals for IT Tasks
Public cloud models often refuse valid operations like vulnerability scans, firewall audits, or script diagnostics due to generic safety filters. All models on the appliance have vendor refusal vectors removed, ensuring legitimate commands run without artificial blocks while remaining governed by your internal policy.
Continuous Upgrades & Open Weights
We continuously evaluate emerging open-weight releases and provide updated model packages. You are never locked in: load any GGUF or native local model into the appliance whenever you choose.
Silicon & Performance
The Hardware
Enterprise local AI performance without $25k+ GPU server costs or datacenter cooling.
The Unified Memory Advantage
Traditional GPU servers cost $25,000 to $80,000, draw over 1,000 Watts, and require datacenter cooling. The SAFi Appliance uses high-bandwidth unified memory to deliver fast local inference in a compact, whisper-quiet aluminum edge appliance drawing under 120 Watts.
Hardware Floor
Guaranteed minimums
- Memory & Compute: 64GB unified memory + 16-Core / 32-Thread processor with dedicated AI acceleration.
- Storage: 1TB PCIe Gen4 NVMe SSD pre-loaded with hardened OS, models, and audit database.
- Networking: 2.5 GbE Ethernet + Wi-Fi 7 (ready for your isolated management VLAN).
- Warranty: 1-Year advance-replacement hardware warranty included.
Software & Security Stack
Ready on first boot
- Hardened SAFi OS: Debian-based system with kernel tuning and Bubblewrap execution sandboxes.
- Identity & TLS: Native Active Directory / LDAP, SCIM 2.0, and local internal-CA HTTPS.
- True Air-Gap: Pull the network cable and all models, agents, and governance tools still run 100% locally.
- 5-Minute Setup: Guided console network setup, then manage via browser or
safi-cli.
Enterprise Control & Audit
The Governance
Governance in SAFi is not an afterthought or a filter, but is the natural result on how the system works.
Your Policies as the Supreme Law
In SAFi, every agent action is governed by an explicit policy written and owned by your organization. The Policy controls the identity and actions the agent is allowed to take.
The appliance includes ready-to-use default policies for the Sysadmin, Security Engineer, and Software Engineer agents. You can tune these rules or create new role policies at any time using the web admin portal.
SAFi is an open framework designed for full auditability and vendor independence. You can inspect the core governance engine on the GitHub repository or visit selfalignmentframework.com.
Controlled Execution
The AI can never run commands on your servers directly. It can only propose actions, which must pass your policy rules and approvals before anything executes.
Model Independence
Your policies, agent roles, and history belong to you, not a cloud vendor. Upgrade or swap AI models at any time, and your governance rules stay intact.
Built-In Threat Defense
Screens incoming prompts and commands for attacks, prompt injections, and sensitive data exposure before processing them, keeping your systems safe.
Complete Audit Trail
Every action, tool call, and policy decision is permanently recorded in a tamper-proof local log, giving compliance officers and auditors the exact proof they need.
Enterprise Oversight & Regulatory Compliance
Designed for regulated enterprises: SEC 17a-4 & FINRA 3110 (tamper-evident WORM audit records), HIPAA & CMMC (zero cloud egress behind local firewalls), and EU AI Act & ISO 42001 (continuous audit trails and human supervisory oversight).