Alex

[Alex @alex_devx]

@opencode I don’t see it?

[Rob Pruzan @RobKnight__]

Introducing terminal-code: VS Code inside the terminal

- VS Code compatible CLI
- works over ssh
- syncs with your terminal theme

https://t.co/j3HThPdVPw

[Nix0n @UnTalNixon_exe]

🚨 Alibaba acaba de open-sourcear el sandbox que todos los agentes de IA necesitaban… y ya es #1 en GitHub Trending.

OpenSandbox = entornos aislados de verdad para que tus agentes:
• Ejecuten código
• Naveguen la web
• Controlen escritorios completos
• Corran Claude Code / Cursor / Codex / Gemini CLI

SDKs en 5 lenguajes (no solo Python), Docker + Kubernetes, gVisor/Kata/Firecracker, Credential Vault y MCP server listo.

12.5k+ stars y subiendo. 100% free & Apache 2.0.

Esto es infraestructura real para agentes autónomos, no otro toy.

Repoo 👇👇

[DeepSeek @deepseek_ai]

🧩 DeepSeek Harness v0.1 is now available in Developer Preview!

🔹 We’re opening it up to developers building agent harnesses worldwide and open-sourcing the codebase in MIT license.
🔹 Powered by the Cordis meta-framework, DeepSeek Harness is an agent harness built around one core idea: Everything is a plugin. Models, tools, skills, sessions, sandboxes, filesystems, loops, orchestration, and UI are ALL implemented as plugins, and can be mixed, matched, replaced, and extended.

Try it now!
https://t.co/2YWSvJHhKA

[dodo-reach 🦤 @DODOREACH]

stop sending bad prompts to your Pi coding agent.

you liked pi-clarify, so i published it on npm too:
pi install npm:pi-clarify

it rewrites your prompt before sending, so you spend fewer turns explaining what you meant

here's how it works

[Kirill @kirillk_web3]

https://t.co/RLeKuCzuFa

[Cloudflare @Cloudflare]

We created the Cloudflare Codex, a governed body of engineering standards that AI agents consume across the development lifecycle. https://t.co/uagE5pWgUt

[Peter Pistorius @appfactory]

Sidequest for Pi is a context aware side channel for coding agent tangents:

It's better /btw.

Ask questions grounded in your active Pi session, and keep the main conversation focused. Hit the ~ key to show/hide the threaded conversation UI.

> pi install npm:pi-sidequest

[UndreamedPanic @UndreamedPanic]

Gamma Emerald - Early Access!

[Miguel Salinas @Vercantez]

https://t.co/pGb77Ubtdp

[Burke Holland @burkeholland]

You're not behind. There's no secret everyone else has.

There's just the harness, and it's mostly all you need.

https://t.co/PXQv3KHpu1

[Alex @alex_devx]

@0xCodez People are putting funny new names to choreography and orchestration which are software architecture integration pattern since dawn of time

[Jensen Huang @JensenHuang]

For my first post, I’m sharing a letter @NVIDIA signed on why open models matter.

AI will transform every industry, power every company, and be built by every country.

Open models strengthen safety and cybersecurity, accelerate innovation and diffusion, and enable sovereignty.

The world needs both frontier closed models and frontier open models.

https://t.co/AUKzoQ5Ikb

[Claude @claudeai]

The Claude Security plugin for Claude Code is now available in beta.

Scan your changes for vulnerabilities before you commit, or run a full scan across your codebase, all from your terminal on the Claude inference you already run.

[0xMarioNawfal @RoundtableSpace]

Unlimited-OCR is a 3B parameter model that parses entire 100-page PDFs in one shot — no page chunking, no lost context.

+⁠32K context window, reads the whole document in a single pass
+⁠93% on standard parsing benchmarks, +6 over baseline
+⁠Under 0.11 error rate past page 40 — where every other OCR tool falls apart
⁠+Multilingual out of the box, runs locally via Transformers, Ollama, llama.cpp, Docker
+⁠Textract, Google Vision, and Azure Doc Intelligence charge $1.50–$15 per 1,000 pages

1.9M downloads on HuggingFace and most people have never heard of it.

This runs on your machine. For free. Forever.

Model link: https://t.co/UKL1bNSXmn

[Claude @claudeai]

Introducing a new way to reflect on how you use Claude.

Your monthly recap shows when you use Claude most and what you spent that time working on, with options to set quiet hours and nudges to take breaks. Find your dashboard in Settings under Reflect: https://t.co/8QAn47W5rI

[CyrilXBT @cyrilXBT]

https://t.co/kdGFjAbZd0

[Yarchi @undefinedKi]

https://t.co/KADozFhjGF

[Akshay 🚀 @akshay_pachaar]

Web scraping will never be the same.

(100% open-source visual search at scale)

PixelRAG is a retrieval system that skips HTML parsing completely.

Instead of scraping a page into text and embedding chunks, it screenshots the page and retrieves the image. A vision-language model reads the answer straight off the pixels.

Why that matters: parsing is where web RAG quietly loses information.

- A single HTML-to-text parser can drop 40%+ of a page.
- Tables, charts, and layout get flattened or thrown out.
- Swapping parsers alone can move accuracy ~10 points on the same docs.

PixelRAG indexes the page a person actually sees. The team built a visual index of all of Wikipedia, 30M+ screenshots, and it still beats the strongest text RAG baseline by 18.1% on text-only QA.

The repo also ships a Claude Code plugin that gives Claude eyes.

It lets Claude screenshot any URL and read the rendered page instead of scraping the DOM. So you can hand it a live page, an arXiv paper, or your local site and ask what it actually looks like.

One setup script. No MCP server, no backend.

How the pipeline works:

- Renders each document (web, PDF, image) to image tiles.
- Embeds them with Qwen3-VL-Embedding, LoRA fine-tuned on screenshots.
- Builds a FAISS index and serves a search API.

A stronger reader model lifts accuracy with no re-indexing, since the index is just pixels.

Everything is open-source under Apache-2.0.

GitHub repo: https://t.co/qun9TjAdmw

Talking about RAG, I recently wrote an article on a new approach that makes retrieval much more efficient by cutting corpus size by 40x, reducing tokens per query by 3x, and improving vector search relevance by 2.3x.

The article is quoted below.