William Mendonça

[Robert Courson @robertcourson]

introducing dynamic workflows for codex.

it's the same things you love about claude code's dynamic workflow feature, but as a codex plugin/skill.

live on github (below)

[HackerNoon | Learn Any Technology @hackernoon]

A look at how engineering organizations are incorporating connected AI tools into software development workflows, observability practices, and operational processes: https://t.co/dan87H77gW

[Ram Maheshwari @rammcodes]

Bruh… this File-Tree component is ridiculously polished 🌳

Trees is an open-source file tree system for building IDE-style file explorers with search, drag-and-drop, file selection, Git status indicators, and more.

Perfect for code editors, developer tools, file managers, and apps that need a modern file explorer UI :)

Follow @rammcodes for more 💎

#html #ai #javascript #coding #webdevelopment #programming

[Software Mansion @swmansion]

Run pose estimation on-device in your React Native app! 🦾

RN ExecuTorch v0.9 has the usePoseEstimation hook that detects human bodies and maps keypoints.

See the demo and full release notes ⬇️

[Nett0 @nett0eth]

imagina que a API do Claude era uma cozinha industrial.

antes, pra pedir um prato, você precisava saber cozinhar: escrever código, configurar autenticação, montar a requisição na mão.

agora a Anthropic colocou um balcão na frente dessa cozinha.

o balcão chama ant.

você faz login uma vez, e a partir daí qualquer chamada pra API vira um comando simples no terminal. mensagens, agentes, arquivos, sessões… tudo acessível sem precisar abrir editor de código.

o Claude Code já vem integrado com o ant. você fala “lista minhas sessões de agente” e ele executa o comando sozinho, lê o resultado e te responde.

pra quem trabalha com agentes em produção: dá pra salvar a configuração do agente em um arquivo YAML, colocar no Git e deixar o CI fazer o deploy automaticamente com um único ant beta:agents update.

instala pelo brew, curl ou go:
https://t.co/CoPAygAM2K

[Aiden Bai @aidenybai]

the problem with React's useEffect

[ClaudeDevs @ClaudeDevs]

Claude Code knows how to use ant using the built-in "/claude-api" skill

Ask it to list your sessions, upload a folder of PDFs, or debug a run.

It shells out to the CLI and reads the results back without any glue code.

Install with brew, curl, or go: https://t.co/II6ZsHU7Qc

[ClaudeDevs @ClaudeDevs]

We’ve added a CLI for Claude Platform to make every API endpoint runnable from your terminal.

Call the Messages API, stand up Claude Managed Agents, pipe results straight into your shell.

The ant CLI is well understood by coding agents (Claude Code) using the claude-api skill.

[0xMarioNawfal @RoundtableSpace]

THE WINNER OF THE ANTHROPIC HACKATHON JUST OPEN SOURCED HIS ENTIRE AI CODING SETUP FOR FREE. 183 AGENT SKILLS, 48 SUB-AGENTS AND 79 READY-MADE COMMANDS.

He spent 10 months on it, won $15K in API credits, then released the whole stack under MIT license.

[Erick @ErickSky]

Tu reverse proxy ideal ya existe.

GoDoxy detecta contenedores automáticamente, los duerme cuando no los usas, integra Proxmox y tiene WebUI.

Escrito en Go.

Un curl y listo.

REPOOO👇

[周览资源 @grgerwcwetwet]

用 Claude Code 写代码的人，真的建议把 Trellis 装上。

不夸张地说，它可能是 Claude Code 的“最佳外挂”之一。

很多人觉得 AI 编程不稳定，其实不是 Claude 不行，而是你每次都在让它“失忆开工”：项目背景要重新讲、需求要重新喂、代码规范要重新说、上次做到哪也要重新解释。

Trellis 直接把这个问题干掉。

它会在项目里生成一个 .trellis/ 目录，把需求、规范、任务、进度、工作日志全部沉淀下来。下次 Claude Code 再进来，不用你从头解释，它能直接读取上下文，知道项目要干什么、做到哪一步、接下来该怎么推进。

这就很像给 Claude Code 装了一个“项目大脑”。

它不是简单的提示词模板，而是一套完整的 AI 开发工作流：先规划，再实现，再验证，最后把经验继续写回项目里。

适合什么人？

长期用 Claude Code 写项目的人；
经常被 AI 忘记上下文折磨的人；
项目越来越大、提示词越来越乱的人；
想让 AI 真正像团队成员一样持续干活的人。

Claude Code 单独用，像一个很聪明但健忘的程序员。
加上 Trellis，才开始有点“AI 开发团队”的味道。

GitHub：https://t.co/GLgQPxx9yX

[CopyRebeldia @CopyRebeldia]

Repo open-source de @webadderall:

https://t.co/ehbh2Mk4lV

[CopyRebeldia @CopyRebeldia]

Los founders que saben codear pero envían demos con cursor de Windows acaban de quedarse sin excusa.

Un repo open-source graba tu pantalla, mete zooms automáticos, pule el cursor y pone fondos cinemáticos. 15.5k estrellas.

Se llama Recordly.

[ALX 🇺🇸 @alxui_ux]

The Smoothest Mobile UI Animation I've Seen This Year 🤯

[FHILY👑 @Oluwaphilemon1]

AI coding agents can now extract any website's design system directly from the terminal.

I love small projects like this that Hyperbrowser creates. Their repo is full of them.

[TANSTACK @tan_stack]

TanStack AI now runs on react-native! 🚀

Stream down to mobile devices with ease using fetch + polyfills or XHR transports!

Try it out with the latest releases!

[Expo @expo]

🆕 Today we open up the beta for our new mobile Observability service.

If you've ever shipped a release and felt uneasy for the next 24 hours...this service is for you.

@kadikraman's App.js talk from today goes into excellent detail. We'll share that link below and a page where you can get started with the beta ↓

[William Mendonça @WillMendoncaDev]

@a_saifut @Danny_H_W @callstackio @mrousavy @margelo_com Is the repack in Webpack or does it already work with Metro?

[Rozzabuilds @rozzabuilds]

My favorite Claude Code tool is back!

If you're not using /simplify as part of your workflow yet, you're missing out.

It scans the pending changes with parallel agents checking for:

- Reuse: finds duplicated logic and missed abstractions.

- Quality: flags readability issues, redundant patterns and structural problems.

- Efficiency: detects performance issues, wasted resources, and easy optimizations.

It then aggregates the results and apply the fixes automatically.

Drop it into your workflow and let it clean up after a session.

Well worth the tokens.

[CJ Zafir @cjzafir]

Do something different this weekend.

Become a PRO in AI Model Fine-tuning.

Paste this prompt in Codex/ChatGPT/Claude/Grok.

"You are an expert AI engineer and teacher.

Your job is to teach me modern LLM engineering and fine-tuning concepts from beginner to advanced level using very simple daily-life language.

Teach me step-by-step like a real mentor. Assume I am smart but new to the topic.

Foundations:

- LLM basics
- How AI models work
- Tokens
- Tokenization
- Context windows
- Embeddings
- Transformers
- Attention mechanism
- Parameters
- Training vs inference
- Open-source vs closed-source models

Datasets & Training:

- SFT datasets
- Instruction tuning
- Preference datasets
- Synthetic datasets
- Data curation
- Dataset cleaning
- Dataset formatting
- Fine-tuning basics
- Continued pretraining
- Hallucination reduction

Fine-Tuning:

- LoRA
- QLoRA
- DPO
- RLHF
- Quantization
- Model checkpoints
- Adapter tuning
- GGUF models

Inference & Optimization:

- KV cache
- Flash Attention
- Speculative decoding
- Inference optimization
- Model serving
- Batch inference
- GPU basics
- VRAM basics
- Latency vs quality tradeoffs

Local AI Ecosystem:

- llama.cpp
- Ollama
- vLLM
- MLX
- Hugging Face
- Unsloth
- Axolotl
- PEFT
- TRL library

RAG & Memory:

- RAG
- Vector databases
- Chunking
- Retrieval pipelines
- AI memory systems
- Semantic search

Agents & Workflows:

- Prompt engineering
- System prompts
- Tool calling
- Function calling
- AI agents
- Agentic workflows
- Multi-agent systems
- Browser agents

Model Types:

- VLMs
- SLMs
- Dense models
- MoE models
- Coding models
- Reasoning models

Deployment:

- Local inference
- On-device AI
- API serving
- Cloud GPUs
- Edge AI basics

Evaluation:

- AI benchmarks
- Human evals
- Cost-per-token analysis
- Speed benchmarking
- Quality benchmarking

Real-World Skills:

- Building chatbots
- Building AI copilots
- AI automation
- AI SaaS workflows
- AI coding workflows
- AI orchestration systems
- AI product thinking

Start from the absolute basics and gradually make me advanced.

Rules:

- Use simple English only
- Avoid academic jargon unless necessary
- Explain every difficult word in plain language
- Use real-world analogies and daily-life examples
- Use small code snippets when useful
- Show practical use cases
- Compare concepts side-by-side when helpful
- Teach from fundamentals first, then advanced concepts
- At the end of each topic:
- give a short summary
- give a simple mental model
- give beginner mistakes to avoid
- give a small exercise/project

I want deep understanding, not memorization."

Thank me later.