The Pulse.
Distilling the chaos of the AI frontier into signals that matter today.
Last Brew Time: Apr 14, 2026, 5:36 PM PT
Anthropic Mythos Limited Release and Government Response
OpenAI pivots toward Amazon partnership over Microsoft
OpenAI Launches GPT-5.4-Cyber for Defensive Cybersecurity
Microsoft 365 Copilot Always-On AI Agents
Google Gemini Personal Intelligence Global Expansion
Google Commits $1 Billion to AI Workforce Training Across Manufacturing, Healthcare, and Education
Oracle's 2.8 GW Bloom Energy Fuel Cell Deal Reshapes AI Data Center Power
Google Chrome Skills: Reusable Gemini AI Prompts
NVIDIA Ising: First Open-Source AI Models for Quantum Computing
Claude Code Routines: Anthropic's Autonomous Developer Automation Launch
Google DeepMind Releases Gemini Robotics-ER 1.6
Trending
Product Hunt
Krisp Accent Converter for YouTube
YouTube has speed control, captions, auto-translate — but no accent control. Now it does. Free Chrome extension, on-device AI, one toggle.
Luma Agents
AI agents that plan, generate, and iterate across video, image, and audio in one pipeline. Brand campaigns, product visuals, social ads, video localisation with shared context end-to-end. For creative teams and agencies.
Cleo Labs
Selling physical products globally? A single item can trigger 100+ regulations across materials, labeling, certifications, and customs and every rule changes from one country to the next. Cleo maps your full regulatory perimeter automatically. Our multi-agent AI pipeline (MARIA) scans 19,000+ authorities in 106 countries and delivers structured compliance maps, verified by legal experts, not hallucinated by a chatbot.)
Skills Janitor
9 commands that audit, deduplicate, lint, fix, and track your claude code skills. shows you what's broken, what overlaps, and what you never touch. free. open source.
showmd
Ever asked yourself why all of those SKILL.md files are rendered in plain text in MacOS Preview? showmd is a free, native macOS Quick Look extension that renders Markdown beautifully. YAML frontmatter parsed into a collapsible metadata table — collapsed by default, one click to expand. No other viewer does this. Agentic AI XML tags — and 17 more — rendered as labeled, bordered blocks instead of raw angle brackets.
ContextPool
Every AI coding session starts from scratch. You re-debug the same bugs, re-explain decisions you already made. Your agent forgets everything. ContextPool gives your agent persistent memory. It scans your past Cursor and Claude Code sessions, extracts engineering insights (bugs, fixes, design decisions, gotchas), and loads relevant context via MCP at session start. No prompting needed. Works with Claude code, Cursor, Windsurf, and Kiro. Free and open source - team sync available for $7.99/mo.
GitHub Trending
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into future sessions.
The open-source voice synthesis studio
Create and share 3D architectural projects.
Python tool for converting files and office documents to Markdown.
An agentic skills framework & software development methodology that works.
skills.sh
find-skills
This skill helps you discover and install skills from the open agent skills ecosystem.
vercel-labs/skills
vercel-react-best-practices
Comprehensive performance optimization guide for React and Next.js applications, maintained by Vercel. Contains 69 rules across 8 categories, prioritized by impact to guide automated refactoring and code generation.
vercel-labs/agent-skills
frontend-design
Distinctive, production-grade frontend interfaces that reject generic AI aesthetics.
anthropics/skills
web-design-guidelines
Review files for compliance with Web Interface Guidelines.
vercel-labs/agent-skills
remotion-best-practices
Domain-specific knowledge base for building videos with Remotion and React.
remotion-dev/skills
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
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...
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
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...
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...
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
Agent Browser
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection