Hacker News

Subscribe to Hacker News feed
Hacker News RSS
Updated: 41 min 28 sec ago

Show HN: OmniGlass – Executable AI screen snips with kernel-level sandboxing

Mon, 03/02/2026 - 6:51pm

I kept running into the same annoying friction with Claude Desktop and Cursor: I’d snip a Python traceback, the AI would tell me to "run pip install pandas," and then I’d sit there and type it out myself. If the AI clearly knows the fix, why am I doing the typing?

So I built OmniGlass.

The UX is simple: You draw a box on your screen, local OCR extracts the text, and an LLM classifies what you're looking at. But instead of generating a chat response, it gives you an action menu.

The core difference from Claude Desktop isn't the AI—it’s what happens after the AI thinks. Claude reads your screen and writes you a paragraph. OmniGlass reads your screen and runs the command.

What it does today:

Snip a traceback → Generates the fix command, you confirm, it runs.

Snip a data table → Opens a native save dialog and spits out a clean CSV.

Snip a Slack bug report → Drafts a GitHub issue with all the context filled in.

Menu bar input → Type plain English, and it triggers the appropriate command.

The security elephant in the room (Why I built this): Nobody is really talking about the security risks of MCP plugins yet. Claude Desktop runs them with your full user permissions. A rogue plugin—or a clever prompt injection—can just read your SSH keys, scrape your .env files, and ship them off.

To fix this, OmniGlass sandboxes every plugin at the macOS kernel level using sandbox-exec. Your /Users/ directory is completely walled off. Environment variables are aggressively filtered. Shell commands strictly require your manual confirmation before executing. I wanted to be able to run community plugins without sweating about what they can access.

The Stack:

Frontend/Backend: Tauri (Rust + TypeScript)

Vision: Apple Vision OCR (local)

Plugin System: MCP over stdio

Models: Works with Claude Haiku, Gemini Flash, or fully local via llama.cpp using Qwen-2.5 (takes ~6s end-to-end, nothing leaves your machine).

Current Status: I just shipped our second working plugin (a Slack Webhook) to run alongside the GitHub Issues plugin. It's two real-world plugins proving the architecture actually works, not just a boilerplate template and a promise. Both are under 250 lines of code.

Where I'd love your help:

Break the sandbox. Seriously. If you can figure out a way to read ~/.ssh/id_rsa from a plugin, that is a critical bug and I want to know about it.

Build a plugin. There are 8 open issues in the repo right now with full MCP schemas, manifests, and implementation hints. Most take less than 100 lines.

Port to Windows/Linux. The Windows build compiles in CI but hasn't been tested on real metal. Linux needs Tesseract + Bubblewrap to replace the Apple OCR and sandbox.

Requires macOS 12+ right now. Fully open source (MIT).

Would love to hear your thoughts or answer any questions about the sandboxing setup!

Comments URL: https://news.ycombinator.com/item?id=47225983

Points: 1

# Comments: 0

Categories: Hacker News

Make it Shitty [video]

Mon, 03/02/2026 - 6:46pm
Categories: Hacker News

Fast Biology Bounties

Mon, 03/02/2026 - 6:14pm
Categories: Hacker News

Show HN: Parallax – Coordinate adversarial AI agents over durable streams

Mon, 03/02/2026 - 6:04pm

Parallax is a CLI for orchestrating independent AI agent cohorts (Claude, Codex, etc.) over isolated, append-only logs or streams. Each cohort operates on its own log and does not see the intermediate reasoning of others i.e. disagreement is enforced at the infrastructure layer rather than prompted at runtime. Agents write to sequenced, durable logs and a separate moderator agent subscribes to all streams, monitors progress, issues steering instructions when necessary, and synthesizes outputs at the end.

That means, coordination is just done over a log with natural language, which allows us to rewire topology of agents mid-run, fork, merge, spawn breakout rooms or build any research methodology on the fly depending on the question. If something goes wrong / crashes, agents can resume from where they left off. Further, if the log or stream is serverless, agents can connect over the log from any machine anywhere in the world and collaborate on tasks / research.

Comments URL: https://news.ycombinator.com/item?id=47225510

Points: 1

# Comments: 0

Categories: Hacker News

Is Code Still Relevant?

Mon, 03/02/2026 - 5:58pm
Categories: Hacker News

Show HN: We filed 99 patents for deterministic AI governance(Prior Art vs. RLHF)

Mon, 03/02/2026 - 5:56pm

For the last few months, we've been working on a fundamental architectural shift in how autonomous agents are governed. The current industry standard relies almost entirely on probabilistic alignment (RLHF, system prompts, constitutional training). It works until it's jailbroken or the context window overflows. A statistical disposition is not a security boundary.

We've built an alternative: Deterministic Policy Gates. In our architecture, the LLM is completely stripped of execution power. It can only generate an "intent payload." That payload is passed to a process-isolated, deterministic execution environment where it is evaluated against a cryptographically hashed constraint matrix (the constitution). If it violates the matrix, it is blocked. Every decision is then logged to a Merkle-tree substrate (GitTruth) for an immutable audit trail.

We filed 99 provisional patents on this architecture starting January 10, 2026. Crucially, we embedded strict humanitarian use restrictions directly into the patent claims themselves (The Peace Machine Mandate) so the IP cannot legally be used for autonomous weapons, mass surveillance, or exploitation.

I wrote a full breakdown of the architecture, why probabilistic safety is a dead end, and the timeline of how we filed this before the industry published their frameworks: Read the full manifesto here: https://salvatoresystems.medium.com/the-death-of-probabilist...

The full patent registry is public here: https://aos-patents.com

I'm the founder and solo inventor. Happy to answer any questions about the deterministic architecture, the Merkle-tree state persistence, or the IP strategy of embedding ethics directly into patent claims.

Comments URL: https://news.ycombinator.com/item?id=47225418

Points: 1

# Comments: 0

Categories: Hacker News

Pages