chebyte retweeted
Today we're launching Sunra MCP, with the most accessible pricing in the industry.
Every leading image, video and audio model, right inside Claude, ChatGPT and the AI assistant you already use. Each one at its maker's own API price, with no markup added.
Now is the time to build. Go create something no one has seen before.
chebyte retweeted
We launched OSS Scanner, which gives critical open source projects free, periodic vulnerability scans from our strongest models.
Each finding includes a proof-of-concept, and a patch where possible.
red.anthropic.com/oss-scanne…
1/ Introducing the Cua Spaces SDK.
Every big lab now ships a bot with its own computer: Grok Bot, Muse, dots. None let you bring your own. With Cua Spaces, now you can.
Put Claude Code, Codex or any agent on compute you choose, and run jobs across all your computers at once.
chebyte retweeted
OMG DeepSeek V4.1-Flash-1017 Search & Fetch APIs costs
$0.75 per 1000 calls.
OAI & Anthropic: $10 per 1000 calls.
Grok: $5 per 1000 calls.
Google Gemini: $14 per 1000 calls.
OMG 😧
Replying to @deepseek_ai
🔍 Search & Fetch APIs are now open to everyone!
Powered by our in-house search engine, serving hundreds of millions of requests daily worldwide.
💰 Each endpoint: $0.75 per 1,000 calls.
📖 Docs: api-docs.deepseek.com/guides…
📌 Search & Fetch calls via server-side tools in DeepSeek Harness, Claude Code, and Codex are currently free for DeepSeek API users. Billing starts Oct 31, 2026, at 16:00 UTC.
3/4
chebyte retweeted
Prompt of the day:
Create a pre-commit hook that prevents files over 5,000 tokens. Tokens = bytes/4.
Run only on staged files. Ignore files which are not authored by agents, like lockfiles or codegen.
Provide explicit instructions on how to split files in the error message.
The simplest investment I ever made in my codebase. So good.
chebyte retweeted
🐘 Introducing Postgres Internals in 3D.
🌟 pgrun.dev/pi
Stop reading boring diagrams. Start exploring PostgreSQL.
An interactive 3D map to understand how Postgres actually works.
100% free. Built for developers.
xitter.cf/alxshp/status/21100494…
Introducing PGSync 🐘
Real-time PostgreSQL replication. FREE. OSS
Built in Rust. 🦀
Postgres 16 / 17 / 18.
No extensions. No triggers. No complex setup.
→ snapshot
→ replicate
→ stream changes
→ track WAL
→ recover from crashes
→ resume automatically
→ keep databases in sync
~15 MB RAM during streaming.
Built for developers. Built for AI agents.
Open source.
xitter.cf/alxshp/status/21078790…
chebyte retweeted
New from Vercel Labs: tsc-ts
TypeScript was written in TypeScript
Then rewritten in Go
We ported it back to TypeScript
Compiled it with scriptc
And it's 2-4x faster than tsgo
Introducing Supabase Middleware.
Write per-request logic once, like checking who's calling, and run it on any runtime that has fetch. The same middleware also works inside Hono, H3, Elysia, NestJS, and TanStack Start with a bridge you copy.
Learn More ↓
supabase.com/blog/supabase-m…
chebyte retweeted
Apple calls the iPad a computer.
So I built Linux for it.
I built LinPad OS - Linux for iPad.
- Desktop windows + a real terminal
- No jailbreak. No VM.
Free & open source (pre-release).
What is your iPad missing?
linpados.com
#Linux #iPad #OpenSource
Highly recommend installing the new TasteSkill v2 in Claude Code or Codex, then having Opus 5.5 use it to 𝗴𝗶𝘃𝗲 𝘁𝗵𝗲 𝘀𝗶𝘁𝗲 𝘆𝗼𝘂 𝘃𝗶𝗯𝗲-𝗰𝗼𝗱𝗲𝗱 𝗮 𝗰𝗵𝗲𝗰𝗸𝘂𝗽. It came out two days ago. It opens your pages at desktop, tablet and phone widths and lists every AI-website tell they hit.
A few on the list you can check right away:
→ A small all-caps line above the headline, like FEATURES
→ Sections numbered 01 / 02 / 03
→ Monospace body text and buttons, anywhere outside code
→ Gradients, hairline borders, and shadows that sit there even without hover
→ Cream backgrounds with terracotta, or any violet or indigo
→ Fewer than 4 real pictures (SVG drawings don't count), or fewer than 8 things that move
New tests: blind judges gave pages built with it 7.7 and pages without it 7.8, 𝗻𝗲𝗮𝗿𝗹𝘆 𝗮 𝘁𝗶𝗲. It still came first on 2 of the 3 briefs.
Send this to Opus 5.5 and it'll list every issue with the page and element it's on 👇
"Install taste-skill by following the README at github.com/Leonxlnx/taste-sk… (the install name is design-taste-frontend), then read its skill file and scripts.
Then run this project locally and run inspect.mjs once each on the homepage and the main landing pages: inspect.mjs --out .taste-skill/inspect/. Look at the screenshots it saves. Only check public-facing pages; skip dashboards and table pages. If Node 22 or Chrome is missing, tell me first.
For each issue, say which page, which width and which element (quote the report), and give the smallest fix. List FAIL items before WARN items.
Show me the list first. Don't change any code."
Opus 5.5 can make top-tier web design, as long as you 𝘀𝗵𝗼𝘄 𝗶𝘁 𝘁𝗼𝗽-𝘁𝗶𝗲𝗿 𝗱𝗲𝘀𝗶𝗴𝗻 𝗳𝗶𝗿𝘀𝘁.
If your pages still look AI-made at a glance, it probably hasn't seen the kind of design you like.
𝗦𝘁𝗲𝗽 𝟭: pick 3 to 5 sites you like on Godly, Refero or One Page Love, drag the screenshots straight into Claude Code, and have it tell you what makes each one look good.
𝗦𝘁𝗲𝗽 𝟮: turn the parts you pick into a DESIGN.md and import it into CLAUDE.md. Every page after that follows it.
𝗦𝘁𝗲𝗽 𝟯: install two design skills:
→ taste-skill (90k+ stars): use it while building, so its pages stop looking like templates
npx skills add Leonxlnx/taste-skill --skill design-taste-frontend
→ Impeccable (70k+ stars): finish each page with /impeccable polish
Run npx impeccable install in your project root, then /impeccable init in Claude Code
Before you ship, send it the full post quoted below and let its subagents check everything once more.
When you send the screenshots, add this 👇
"These are screenshots of sites I like. Don't touch any code yet:
1. For each one, tell me what it does well: layout, typography, color, spacing, white space.
2. List what they have in common, ask me which parts I want, and wait for my answer before going on.
3. Write a DESIGN.md in the project root based on what I pick, with real values: font sizes, weights, color codes, spacing, corner radius. Mark anything you can't tell from the screenshots as an estimate. Don't make it up. Keep it short, one screen at most.
4. Import DESIGN.md into the root CLAUDE.md with an @ line, not inside backticks. Then add a rule: after every page you finish, run /impeccable polish."
Python is now available on Vercel.
Unlock the full potential of your agents and get started with the eve Python Agent featuring a Next.js frontend and FastAPI backend.
vercel.com/templates/eve/eve…
did you know you can submit Grok Bot (and Grok, Cursor) plugins? submit them here!
x.ai/bot/marketplace/submit-…
Don’t babysit your agents. Put them in sandboxes. Each sandbox is a microVM with its own kernel. And now they run in the cloud, too.
Ready to try it out? New signups get $250 in Cloud Sandboxes credit. Claim yours before the promotion ends on October 31: docker.com/c/sbx-promo/
chebyte retweeted
Claude Code can now use almost any app on your computer, not just your code.
CLI-Anything wraps desktop software in a command line an AI agent can operate: GIMP, Blender, LibreOffice, Calibre and a growing list of community-built ones.
→ CLI-Hub works like an app store for agent-ready tools
→ No CLI for your app yet? A plugin generates one
→ Works with Claude Code, Cursor, Codex, OpenClaw and more
Try one in two commands:
pip install cli-anything-hub
cli-hub install gimp
Add the generator to Claude Code:
/plugin marketplace add HKUDS/CLI-Anything
/plugin install cli-anything
You still need the real app installed: GIMP for the GIMP CLI, Blender for the Blender one.
52K+ GitHub stars. Apache-2.0.
github.com/HKUDS/CLI-Anythin…
chebyte retweeted
SDK v0.28.0 introduces a persistent browser tool for Agents. Your agent can now keep tabs, cookies, and login sessions alive between turns instead of starting a fresh session every time.
developers.cloudflare.com/ch…
chebyte retweeted
We've been working hard on making the Claude Code desktop app great for running lots of sessions side by side.
It's now much quicker to start sessions, easier to split work across a few, and you can always see what each of them is doing. Here’s what's new:
chebyte retweeted
Introducing Grok Voice 3.0, the world’s most intelligent speech-to-speech model.
It excels at resolving customer calls, responds in under a second, and costs less than other frontier models.
chebyte retweeted
Anthropic released code-modernization v1.0.0, a Claude Code plugin for modernizing legacy codebases
Save this post if you have a legacy project worth modernizing
What I find interesting is that it doesn’t just rewrite code. It tries to prove the new implementation behaves like the original
Here’s how:
- Analyzes the legacy system and extracts business rules
- Generates a modernization plan for your approval
- Rewrites or upgrades the code, even across languages
- Runs the old and new implementations with identical inputs and compares outputs
- Generates additional edge cases to test behavior
- Introduces deliberate bugs to verify tests actually catch them
- Produces a verification report with PROVEN, PARTLY PROVEN, or NOT PROVEN results
It also keeps the original code untouched and requires human approval at critical steps
I think this is the right direction for AI-assisted modernization, generating new code is one thing
Proving that you haven’t broken existing behavior is a completely different challenge
Install:
/plugin install code-modernization@claude-plugins-official
Repo:
github.com/anthropics/claude…



























