Discover the Best AI Resources

Pocket TTS

Generates low-latency, streaming text-to-speech entirely on CPUs (no GPU or cloud API required), using an ~100M-parameter model with voice cloning and multilingual support. Optimized for low resource use (2 CPU cores, ~200ms to first audio chunk) — suited for local, privacy-sensitive, or embedded TTS.

SGLang-Omni

Orchestrates low-latency, multi-stage pipelines for omni and multimodal models by running each stage with its own scheduler and using zero-copy shared memory for tensor transfer. Emphasizes per-stage bottleneck tuning and OpenAI-compatible streaming endpoints, suitable for TTS and multimodal serving.

World Monitor

Aggregates global news, infrastructure, military and market signals into an interactive map dashboard and synthesizes AI-generated intelligence briefs. Key features: local/remote LLM support, 3D globe + flat map, 35+ data layers, country instability index and client-side RAG/embeddings.

Astryx

Provides a customizable React-based design system and component library designed for people and AI assistants to build together. Ships 150+ accessible components, a theme system, and a CLI; supports swizzling to eject source and className overrides so projects avoid styling lock-in.

Claude Code Ultimate Guide

Provides a comprehensive, security-first guide and template library for using Claude Code — from core concepts and agentic workflows to production hardening. Includes threat DB (CVE mappings), 219 templates, 271-question quiz, and interactive diagrams.

oh-my-claudecode

Teams-first orchestration layer for Claude Code that runs, coordinates, and parallelizes multi-agent workflows from the CLI/tmux. Features team pipelines, skill extraction, provider adapters (Codex/Gemini), and realtime HUD for developer-focused automation.

daily_stock_analysis

Generates daily LLM-powered decision dashboards for A/H/US stocks by combining multi-source market data, real-time news, technical signals and agent-style strategy reasoning; deploys via GitHub Actions or Docker and pushes reports to multiple channels.

Stop Slop

Teaches LLMs to detect and remove “AI tells” from prose using curated phrase/structure lists, before/after examples, and a 5‑dimension scoring rubric. Delivered as a reusable skill (SKILL.md + reference files) designed to plug into Claude or any LLM workflow for automated style sanitization.

Awesome Codex Skills

Modular collection of Codex 'skills' that let Codex execute real workflows (emails, issues, Slack posts, data tasks) via the Codex CLI/API. Curated, metadata-driven skill bundles enable discoverability and quick installation for automating terminal-to-app actions.

Engram — Conditional Memory via Scalable Lookup

Provides a conditional memory module that performs O(1) N‑gram lookups and fuses static embeddings into transformer hidden states — enables offloading large embedding tables to host memory with minimal inference overhead.

Multica

Turns coding agents into assignable teammates that pick up issues, run on local or cloud runtimes, stream progress, and convert solutions into reusable skills; vendor-neutral, self-hostable platform with a local daemon and multi-workspace board.

baoyu-skills

Collection of modular 'skills' for Claude Code that automate content creation, image/slide/infographic generation, and platform publishing. Provider-agnostic image & AI backends, browser-based publishing adapters (X, WeChat, Weibo), and ClawHub publishing support. Requires Node.js and Claude Code.