A curated collection of noteworthy tools, articles, and resources from across the web — searchable, organized, and enriched with AI analysis.
Showing 49-72 of 1252 bookmarks
All Stories
Docs, benchmarks and setup notes for ds4, antirez’s C inference engine for DeepSeek V4/V4.1, Qwen3.8 Flash Next and GLM 5.x on Metal, CUDA and ROCm.
Based on the beloved book series by Arnold Lobel. Frog and Toad are not at all alike. Frog likes new adventures. Toad likes the comforts of home. Yet …
Agentic tooling for Sentry. Contribute to getsentry/toolkit development by creating an account on GitHub.
Improve the AI-written code in all your SwiftUI projects with my free agent skill
Pi Durable is a new experimental package for long-running, durable, and malleable agents that can run anywhere. A tour of what we built and why.
Your always-on AI coworkers that move between text, calls, and Slack. - CopilotKit/OpenDots
Strix Halo inference engine. Qwen Flash Next Q4_K_XL: 1,628.52pp, 59.41tg single user, 157.22 tok/s 8 users; Qwen27B Q4_K_XL: 656.33pp, 70.56tg tok/s single user with DFlash2 - gufo-org/gufo
Run Qwen3.8-Flash-Next (180B, 6B active) on a single AMD Strix Halo via the halogen-flash-server container - claudejaune/Qwen3.8-Halogen-Flash-Strix-Halo
Customizable TypeScript testing framework for web, mobile apps and more.
Easy to use OpenStreetMap editor for Android. Contribute to streetcomplete/StreetComplete development by creating an account on GitHub.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
High-performance Lemonade alternative for AMD Strix Halo & Radeon — latest MoE models (Ling-3.0-Flash, Qwen 3.8 Flash Next, Ornith 1.5), bleeding-edge RDNA 3.5 Wave64/ROCmFP4 kernels, and silic…
RDNA-native LLM inference engine in Rust. . Contribute to warpfront/hipfire development by creating an account on GitHub.
/problem-first: a simple skill to invert bad ideas
Autoharness — a self-learning skill layer for Claude Code — distills skills from your real sessions, updates them as you work, and prunes the ones that stop getting used. No daemon, no benchmark. -…
A new training method, model, and benchmark for retrieving answers and their supporting context.
Reflections on trying Anthropic’s new eval plugin for Claude.
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemin…
ComputeSDK Actions replaces the execution layer of GitHub Actions: keep your workflows, choose the providers and regions they run on, and give agents the whole loop from dispatch to rerun.
Contribute to enesgules/dotfiles development by creating an account on GitHub.
Implement event subscriptions and webhook delivery for your MCP server.
Source code and build artifacts sharing verified storage, synchronization, and garbage collection.
AI agents running research on single-GPU nanochat training automatically - karpathy/autoresearch
A codex plugin for running optimization loops inside a codebase. It is useful when you have a measurable target and many possible changes to try: test runtime, build speed, bundle size, model loss,…
