Nadhi Audit
Airgapped AI security auditor & verified code fixes
What it does
Nadhi Audit is the first 100% air-gapped AI security code auditor and AST auto-remediator for macOS. Powered on-device by Apple Silicon Metal GPU, 0 bytes of proprietary source code or secrets ever leave your machine. Scan for OWASP Top 10, CWE, DPDP, HIPAA, and GDPR issues in milliseconds. Nadhi does not just alert; it kinda patches code, passes compiler syntax gates, verifies via a local LLM judge, and opens signed GitHub PRs. Includes built-in MCP server support for Claude Code and Cursor.
Nadhi Audit runs entirely on your Mac's Apple Silicon Metal GPU. Zero bytes of source code leave your machine: no cloud calls, no telemetry, no leaked secrets. On-device audits, AST-verified fixes, and DPDP, HIPAA and GDPR evidence.
Airgapped code security auditing and AST-verified branch remediation running natively on Apple Silicon Metal GPU. 0 bytes of source code ever leave your Mac. Network is used once to shallow clone (read-only). Then the wire is cut. A story-driven walk through the modern code compliance lifecycle. You rotate your API keys today. The AI assistant accesses them tomorrow in your IDE, transmits code to third-party cloud servers, and the endless rotation loop continues. Inference runs completely on Apple Silicon Metal GPU. When cloud AI services are down, your security engine never stops. Zero telemetry, zero external network calls. Nadhi_Audit_FT.gguf is custom-trained to understand Abstract…from convaiinnovations.com
Does the same job
all alternatives →
Sentinel AIJun 2026 · accounts.google.com · ▲2A local-first Mac security auditor that roasts your code.
A local tool that logs every time you swear at your AI coding assistant11d ago · github.com · ▲10A strictly local Claude Code plugin that calculates your Harmony Deviation Index, and preserves the evidence for the coming AI uprising. Zero telemetry. Zero cloud snitching. 100% artisanal developer shame. - fireinbelly/biomass-conversion-index-monitoring-system
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com