The Pulse.

Distilling the chaos of the AI frontier into signals that matter today.

Last Updated: Apr 17, 2026, 5:45 PM PT

Jensen Huang's Dwarkesh interview on China chip sales

TECH

48Signals

Product Hunt

Claude Code Desktop App Redesigned

Claude Code's desktop app is redesigned for parallel agentic coding. Run sessions across multiple repos, review diffs, edit files, and ship without leaving the app. Built for developers running Claude Code on Pro, Max, Team, or Enterprise.

528

#Productivity

X-Pilot

X-Pilot turns docs into video courses for people who explain anything and can't risk hallucinations. Every visual is rendered programmatically via Remotion in isolated sandboxes — deterministic, not generative. Formulas, diagrams, and code stay accurate.

356

#Education

Resend CLI 2.0

Skills for AI agents, React Email support, Automations, and Webhook listening. All from the terminal.

344

#Email

Google Chrome Skills

Skills in Google Chrome turn your best AI prompts into reusable one-click workflows. It lets you discover, save and remix AI workflows and repeat them instantly. Save any prompt from chat history, trigger it with / or +, and run it across the page or multiple tabs. Includes a ready-to-use Skills library you can customize. From shopping comparisons to productivity boosts, streamline browsing with smarter, repeatable AI actions.

258

#Task Management

Fellow for iOS

Fellow for iOS turns your phone into a powerful AI note taker. Record any meeting without a bot or computer: Fellow handles the transcription and AI note-taking automatically. Before meetings, prep with Ask Fellow, edit agendas, and set your recording preferences right from your calendar. Afterward, replay audio and video, read through transcripts and notes, and manage action items by accepting AI suggestions or creating your own.

215

#iOS

stagewise

stagewise is an open-source coding agent that can actually see your app. It works in its own browser environment, reads the DOM and console, and edits the code behind what it’s looking at. Use any model, bring your own key, and keep full control.

182

#Open Source

GitHub Trending

EvoMap/evolver

The GEP-Powered Self-Evolution Engine for AI Agents. Genome Evolution Protocol. | evomap.ai

JavaScript

4.0K

lsdefine/GenericAgent

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

Python

3.5K

SimoneAvogadro/android-reverse-engineering-skill

Claude Code skill to support Android app's reverse engineering

Shell

2.7K

BasedHardware/omi

AI that sees your screen, listens to your conversations and tells you what to do

Dart

9.7K

Lordog/dive-into-llms

《动手学大模型Dive into LLMs》系列编程实践教程

Jupyter Notebook

31.5K

Donchitos/Claude-Code-Game-Studios

Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.

Shell

11.6K

skills.sh

#11.1M installs

find-skills

This skill helps you discover and install skills from the open agent skills ecosystem.

vercel-labs/skills

#2325.9K installs

vercel-react-best-practices

Comprehensive performance optimization guide for React and Next.js applications, maintained by Vercel. Contains 70 rules across 8 categories, prioritized by impact to guide automated refactoring and code generation.

vercel-labs/agent-skills

#3306.9K installs

frontend-design

Distinctive, production-grade frontend interfaces that reject generic AI aesthetics.

anthropics/skills

#4260.4K installs

web-design-guidelines

Review files for compliance with Web Interface Guidelines.

vercel-labs/agent-skills

#5247.4K installs

remotion-best-practices

Domain-specific knowledge base for building videos with Remotion and React.

remotion-dev/skills

#6210.6K installs

microsoft-foundry

This skill helps developers work with Microsoft Foundry resources, covering model discovery and deployment, complete dev lifecycle of AI agent, evaluation workflows, and troubleshooting.

microsoft/azure-skills

ClawHub

#1394.8K dl

self-improving-agent

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...

★ 3.2K

#2166.0K dl

ontology

Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...

★ 539

#3165.2K dl

Self-Improving + Proactive Agent

Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...

★ 968

#4120.7K dl

Multi Search Engine

Multi search engine integration with 16 engines (7 CN + 9 Global). Supports advanced search operators, time filters, site search, privacy engines, and Wolfra...

★ 566

#5117.8K dl

Polymarket

Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.

★ 78

#689.9K dl

Agent Browser

Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection

★ 322

The Pulse.

Jensen Huang's Dwarkesh interview on China chip sales

Claude Mythos cybersecurity model and White House reset meeting

OpenAI Codex desktop app adds background computer use

Anthropic releases Claude Opus 4.7

OpenAI launches GPT-Rosalind for life sciences

Anthropic launches Claude Design

Anthropic shifts to per-token enterprise billing

Dairy Queen deploys Presto AI voice chatbots in drive-thrus

AI chip startups raise record funding to challenge Nvidia

Google Chrome launches split-screen AI Mode for side-by-side browsing

Cerebras files for IPO

Trending

Anthropic Ships Claude Opus 4.7 + Claude Design, Putting Figma and Enterprise Tools on Notice

Enterprise AI Agents Go Mainstream: Salesforce Headless, Slack Ships Agent Platform, Mac Minis Sell Out

OpenAI's Codex 'Superapp' Push Lands Alongside a Sora/Science Leadership Exodus

xAI Becomes a Cloud Compute Vendor — Supplies Tens of Thousands of GPUs to Cursor for Composer 2.5

UAW + Bernie Sanders + Joe Rogan Forge Anti-AI Labor-Political Coalition Demanding UBI Guardrails

Anthropic's Claude "Mythos" Triggers Global AI Regulation & Security Moves

AI Labs Ship a Product Wave: OpenAI's GPT-Rosalind for Science, Google Gemini 3.1 Flash TTS, Agentic Commerce Goes Live

AI Infrastructure Boom: TSMC Forecast Up, UK Data Center Drama, GPU Supercycle

AI Alignment Resurfaces: Yudkowsky's Return, OpenAI Safety Fellowship Opens, New Research Shows Models Lie Deliberately

Memory Layers & Context Engineering Emerge as the Post-RAG Frontier for AI Agents

OpenAI's Jobs Risk Paper Reignites AI Economics Debate

Curated

5 tips for OpenClaw

Claude Opus 4.7 - A New Frontier, in Performance … and Drama

Anthropic And OpenAI Are Fighting Over Your Memory. You're Going To Lose.

Tech talent is about to get ugly thanks to this memo #ai #tech #competition

State of the Claw — Peter Steinberger

Harness Engineering: How to Build Software When Humans Steer, Agents Execute — Ryan Lopopolo, OpenAI

Building pi in a World of Slop — Mario Zechner

Hermes Agent和OpenClaw有什么区别 | Nous Research | 控制中枢 | Agent自身执行循环 | 自我提升与知识生成 | 分层记忆体系 | 自动化能力 | 抄袭风波

把你的同事炼化成Skill？| Github爆火项目 | 职场打工人 | 什么是Skill | Anthropic | 提示词 | 开放标准格式 | 反蒸馏 | 版权问题 | 静态快照

Opus 4.7 Hit 97% on My Hardest Benchmark

“杭州六小龙”首个IPO、空间智能与AI的下一步：对话群核科技创始人黄晓煌