A curated collection of noteworthy tools, articles, and resources from across the web — searchable, organized, and enriched with AI analysis.
Showing 433-456 of 1253 bookmarks
All Stories
Zig INferenCe Engine — Local LLM inference on AMD GPUs and Apple Silicon - zolotukhin/zinc
Community recipes for serving LLMs on RTX 3090. Multi-engine (vLLM, llama.cpp, SGLang) and model-agnostic. Currently shipping Qwen3.6-27B configs for 1× and 2× cards. - noonghunna/club-3090
Components crafted for Design Engineers. Styled using Tailwind CSS, fully compatible with Shadcn, and easy to integrate—just copy and paste. MIT 🤌 - nolly-studio/cult-ui
Open-source Shadcn UI components, animated blocks, and full templates you can copy-paste into any TypeScript/Next.js project.
Community-submitted local LLM benchmarks. Compare tok/s, TTFT, and hardware efficiency across GPUs, Apple Silicon, and CPU setups.
Lucebox optimization hub: hand-tuned LLM inference, built for specific consumer hardware. - Luce-Org/lucebox-hub
Headless CLI client for stateful Agent Client Protocol (ACP) sessions - openclaw/acpx
A slide framework built for agents. Contribute to 1weiho/open-slide development by creating an account on GitHub.
Search a curated DESIGN.md library for AI agents: colors, typography, spacing, and component patterns from top websites.
Let your agents spend on your behalf. Your payment credentials are never exposed. You approve every purchase. - stripe/link-cli
@aaronjmars posted on X sharing links to the npm package @aaron and the GitHub repository github.com/aaronjmars/ope. The post was made at 4:05 PM on April 29, 2026, and received 166 views. aaronjmars describes himself as "architect of onchain realities" on GitHub.[1]
Assess and monitor risk from AI in vendors with novel intelligence on emerging threats. Stay ahead of AI-driven third-party risk with continuous moitoring and adaptive insight.
Laws of UX is a collection of best practices that designers can consider when building user interfaces.
By Ryan Lopopolo, Member of the Technical Staff
Open-source orchestration for zero-human companies - paperclipai/paperclip
Native desktop automation CLI for AI agents. Control any application through OS accessibility trees with structured JSON output and deterministic element refs. - lahfir/agent-desktop
Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows). - trycua/cua
Spinners for use in the terminal. Contribute to sindresorhus/cli-spinners development by creating an account on GitHub.
Koog's Structured Output API ensures LLM responses conform to defined Kotlin data classes via JSON schema generation and structured requests. Data structures use annotations like @Serializable, @SerialName, and @LLMDescription on classes, properties, nested objects, lists, maps, enums, and sealed classes for polymorphism. The API handles response validation for reliable, formatted data in AI applications.
News and insights on the Android platform, developer tools, and events.
Multi functional app to find duplicates, empty folders, similar images etc. - qarmin/czkawka
Install tailscale subnet router on Firewalla Gold - mbierman/firewalla-tailscale-docker
