REX AI Tool Directory
Complete directory of tool.rexai.top generated from its official sitemap, covering every video, media, JSON, Base64 and publishing helper entry point.
Stop Panicking on Failure: Production‑Ready ink! Events & Error Handling
Beginner‑friendly, production‑oriented ink! walkthrough: emit events for observability, return typed errors instead of panics, and ship with a minimal runnable example plus test assertions.
Tokencake: Multi-Agent KV Cache Scheduling That Cuts vLLM Latency by Half
Beihang/Peking/Alibaba introduce Tokencake, a KV-cache-centric serving framework for multi-agent apps. With time+space scheduling plus CPU buffering and progressive GPU reservation, it trims end-to-end latency by 47%+ versus vLLM and lifts GPU cache utilization by ~17%.
Rust Macros 2.0 Starter Guide: Build Code Like Lego
A panoramic Rust Macros 2.0 guide: unify macro namespaces, master the TokenStream pipeline and macro hygiene, and migrate from macro 1.0 to macro 2.0 metaprogramming with practical examples.
Skill Seeker: Turn Docs Into Claude-Ready Skill Packs (Hands-on Guide)
Stop slogging through docs: convert any framework site into a Claude skill pack in minutes. Practical workflow covering CrewAI, AutoGen, LangGraph and more.
OpenSpec Installation and Project Initialization Guide
How to install and run OpenSpec for this repository and your team: npx (no install), global install, binary/internal distribution, and quick validation steps.
Master OpenSpec in the AI Era: A Practical Guide to SDD (Spec‑Driven Development)
A hands-on, SEO-friendly primer on Spec‑Driven Development with OpenSpec: change proposals, specs, tasks, validation, and release — plus a 10‑minute quickstart and best practices.
Data Science Skills Map for 2026 Newcomers
A hands-on, newbie-friendly roadmap for the skills every data scientist will need in 2026.
Evan You Announces OXC Tools: 45x Faster Than Prettier, 50-100x Faster Than ESLint
Vue.js creator Evan You unveils OXC tool suite with oxfmt 45x faster than Prettier and oxlint 50-100x faster than ESLint, revolutionizing frontend development workflow
Rust Makes Qwen LLM Models Blazing Fast Again: 6x Speed Tokenizer Black Magic
bpe-qwen: BPE tokenization core rewritten in Rust for Qwen models, tested at 6x–12x speedup with HuggingFace API compatibility. One-line replacement to accelerate your inference pipeline.