Air-gapped & high-assurance
Air-gapped AI IDE for teams that cannot use cloud assistants
In air-gapped or export-controlled environments, developers still need AI-assisted coding—without outbound API calls. Quietly runs entirely on-device after initial model acquisition.
Offline after provisioning
Transfer installers, a llama.cpp build and model files through your approved process. Inference needs no network; the license needs one HTTPS check to quietlycode.org at least every 30 days.
Source stays on-machine
Proprietary firmware, defense, finance, and research codebases remain on the workstation—not on a vendor training pipeline.
Documentable posture
Link security reviewers to our Privacy Policy, Terms, and this page for a clear product story.
Deploying in restricted networks
Use standard Quietly installers (.exe, .dmg, AppImage, .deb, .rpm), point first-run setup at a transferred llama.cpp build, and add model files with Models → Import Model where outbound Hugging Face access is blocked.
Plan for the license check: allow www.quietlycode.org through your proxy, or open a brief connection window at least every 30 days. Environments that can never connect should contact us via quietlycode.org/contact before buying.
Evaluation checklist
Confirm offline operation after setup, map data flows (local disk only), and compare against your existing cloud IDE assistant policy.
Quietly integrates llama.cpp, AirLLM, FreeToken and Frontier (Colibri) as inference engines—list the ones you deploy, with their versions, in your software bill of materials. Our air-gapped setup checklist covers the full allowlist.
Guides
Air-Gapped AI for Defence, Government and Regulated Teams: A Setup Checklist (2026)
Under CMMC, any AI that processes controlled unclassified information is in scope. A five-phase checklist for running AI coding and chat on isolated or restricted networks: what to download, how to verify and transfer it, how to prove nothing leaves, and the exact network allowlist for Quietly—including its one honest limitation.
The EU AI Act After August 2026: What Actually Applies to Developers (Post-Omnibus Guide)
August 2, 2026 was meant to be the AI Act’s big day—then the Digital Omnibus moved the high-risk rules to 2027 and 2028 and softened AI literacy. What applies now, which “hat” you wear when you use or ship AI, the transparency duties that did start, and where running AI locally helps (and where it doesn’t).
“Bleeding Llama” Explained: Is Your Local AI Exposed to the Internet? (60-Second Check)
CVE-2026-7482 let anyone on the internet read memory from ~300,000 Ollama servers—prompts, system instructions and API keys included. What happened, why “local” didn’t mean “private”, and a one-minute check you can run on your own machine today.
A Malicious Repo Can Hijack Your AI Coding Agent: Prompt Injection Explained (and How Folder Trust Stops It)
In 2026, a GitHub issue title compromised about 4,000 developer machines, and Mozilla showed a repo with no malicious code that still opens a reverse shell through an AI agent. How indirect prompt injection works, the three doors it uses, and a safe routine for opening code you didn’t write.
Corporate Data Leaks & AI: Is Your Source Code Actually Private?
CTO-grade threat modeling for AI coding tools: what can leak, why it leaks, and how local AI changes the security boundary for proprietary code.
Is That Model File Safe? Pickle vs Safetensors vs GGUF, and How to Download AI Models Without Malware
Researchers have found 1,574 look-alike models on Hugging Face, and 2026 brought critical bugs triggered by poisoned GGUF files. Which model formats can carry code, how fake repos fool people, what a sha256 checksum does—and doesn’t—prove, and a six-point checklist before every download.