@trq212 Good ideas but Still a gadget with some issue on copy pasting, back lines.
I would dream of a rust stack cursor like to manage Claude code session on different project (like the app but local)
Iykyk
thanks! ntfy is a different thing (pub/sub alerts). notifyd is transactional, your app sends email + push + in-app to a user.
multi-channel: channels: ["email", "sms", "in_app"] in one POST.
Novu needs a workflow in their dashboard or their typescript framework for the same thing. makes sense for their enterprise customers who want a visual builder. didn't make sense for me, agents just wanted API or CLI currently.
i used novu for a while. works, but 500mb+ of ram and my agents couldn't manage it without fighting the react sdk and the mongodb/redis setup.
rewrote the whole thing in rust. 30mb of ram, ~500 notifs/sec, one postgres database. one binary.
the thing that actually made the rewrite worth it. /docs/llms.txt. plain text api reference. my coding agent reads it, sets up templates and send calls on its own. no docs browsing, no integration guide.
that's what i couldn't do with novu.
3700 lines, mit, open source
๐จ Screen Studio charges $89 for this. Someone open sourced the entire thing for free.
It's called OpenScreen. 8,400+ GitHub stars.
You record your screen. It automatically transforms it into a polished, professional demo video.
Auto-zoom into clicks. Smooth cursor animations. Motion blur. Custom backgrounds with wallpapers, gradients, and shadows. Webcam overlays. Annotations. Timeline editing. Export in any aspect ratio.
The exact workflow that Screen Studio sells for $89 and Loom sells as a subscription. Free. No watermarks. No accounts. No subscriptions.
Here's what you get out of the box:
โ Full screen or window capture with system audio and mic
โ Automatic zoom that follows your cursor and clicks
โ Manual zoom with customizable depth and timing
โ Smooth motion blur on pan and zoom transitions
โ Animated cursor rendering with motion effects
โ Webcam bubble overlay with drag-and-drop positioning
โ Wallpapers, solid colors, gradients, or custom backgrounds
โ Text and arrow annotations layered over recordings
โ Timeline trimming and variable speed segments
โ Crop, resize, and export in any resolution or aspect ratio
โ Save and reopen projects anytime
Here's the wildest part:
A developer forked it and built an even more advanced version called Recordly. Full cursor animation pipeline. Native macOS and Windows recording. Zoom behavior that mirrors Screen Studio frame-for-frame. Audio tracks. Webcam overlays with zoom-reactive scaling.
Both are free. Both are MIT licensed. Both work on Windows, macOS, and Linux.
Download. Record. Export. Done.
100% Open Source. MIT License.
(Link in the comments)
Okay so I made an open source toolkit for the EU AI Act compliance.
Here's the thing, it's coming (it's already there in fact). GPAI rules kicked in August 2025. Full high-risk requirements hit August 2026. Fines go up to โฌ35M or 7% of global turnover. And most teams I talk to still have no idea what tier their system even falls under.
So I built three things, same data layer, no vendor lock-in:
โ TypeScript SDK: classification, checklists, templates
โ CLI with an interactive classification wizard
โ Web dashboard with timeline + compliance tracking
14 languages supported in the web app.
One command to find out where you stand:
npx @ eu-ai-act/cli classify
Ah, also it's agentic native, so you can just install the skills and ask your favorite agent to use it ;)
Repo below ๐
Can LLMs be PROVABLE computers?
Percepta showed that a transformer can BE a computer. Compiled weights, deterministic execution, 30k tokens/sec.
But nobody asked the obvious follow-up: how do you know it computed correctly?
So I built the verification layer. A STARK that proves it ๐
The 17% drop isn't from using AI.
It's from using AI without structure.
I've been coding with Claude Code daily for 6 months. The difference: I encode my review checklists, debug methodology and ship gates as agent skills.
AI follows MY process. Not the other way around.
Vibe coding = skill atrophy.
Encoded methodology = force multiplier.
The security vs convenience paradox is real.
Run agents on a VPS โ safe, isolated, 24/7. But no browser sessions.
Run agents on your laptop โ full Chrome MCP, live cookies. But your agent has access to everything.
Whoever solves "authenticated browser on a headless server" wins the agent infra game.
Official Chrome MCP support is coming?
I should be able to just `amp mcp add chrome-devtools -- npx chrome-devtools-mcp@latest --autoConnect` and let Claude browse on my behalf, within my login sessions.
Chrome 144 required, it is in "early stable" mode and aiui will get general release only next Wed.
@Starknet just shipped STRK20. Any ERC-20 can now have private balances and transfers. Compliance built in. Hash-based proofs, no trusted setup.
Most people see a DeFi privacy upgrade. I see something bigger.
I used to run a warehouse. EDI orders on FTP servers. SAP IDocs failing at 3am. Master data mismatches that cost weeks to fix. One wrong product code stops the whole chain. Someone opens a CSV, finds a typo, sends three emails.
That's how trillion-dollar supply chains still work in 2026.
If ZK proofs can make tokens private AND verifiable, the same architecture solves the bullwhip effect. Orders proven cryptographically. No master data wars. No information asymmetry between partners.
Private doesn't mean hidden. It means proven without showing the data.
Not a DeFi feature. The biggest B2B infrastructure shift since EDI was invented in 1970.
1/ Privacy for Bitcoinโฆ and for every ERC-20.
Introducing STRK20: a privacy capability that gives any ERC-20 confidential balances and private transfers, with compliance built in.
The market is now one click away from privacy on any token ๐งต