A curated collection of noteworthy tools, articles, and resources from across the web — searchable, organized, and enriched with AI analysis.
Showing 385-408 of 1253 bookmarks
All Stories
JetBrains’ reasoning-augmented code MoE (12B total / 2.5B active) that emits explicit <think> chains for debugging, planning, and agentic coding
Free skills from the Hyperagent team. Contribute to alexmcdonnell-airtable/hyperagent-public-skills development by creating an account on GitHub.
My personal collection of grass fed skills. Contribute to hunvreus/skill-issue development by creating an account on GitHub.
Thermo-nuclear branch review: deep correctness and security audits plus harsh code-quality rubrics, parallel subagents, thermos orchestration, and optiona…
Cursor plugin specification and official plugins. Contribute to cursor/plugins development by creating an account on GitHub.
Use Cursor’s models with any harness. Run Composer through a local OpenAI-compatible API for OpenCode, Codex, VS Code, Cline, Kilo Code, pi, and your own tools.
Official course website for Stanford CS336: Language Modeling from Scratch (Spring 2026), including logistics, schedule, assignments, and course materials.
Student version of Assignment 1 for Stanford CS336 - Language Modeling From Scratch - stanford-cs336/assignment1-basics
Great advice for creating your launch video https://t.co/HUp85FNeC9
Your CLI home video recorder 📼. Contribute to charmbracelet/vhs development by creating an account on GitHub.
PrismML introduces Bonsai Image 4B, a 4B-parameter diffusion image generation model optimized for local inference on devices like iPhones, iPads, Macs, and CUDA GPUs. It comes in two low-bit variants: a 1-bit model with binary transformer weights that reduces the diffusion transformer footprint to 0.93 GB (8.3x smaller than FLUX.2 Klein 4B) and a ternary model at 1.21 GB (6.4x smaller) that preserves about 95% of the original model’s benchmark performance. These models enable on-device generation of 512x512 images in around 9.4 seconds on iPhone 17 Pro Max and about 6 seconds on Mac M4 Pro while substantially lowering memory usage and maintaining competitive image quality versus other 4B-class and smaller models.
Install These Skills Before Codex Touches Your Xcode Project
OpenAI Plugins. Contribute to openai/plugins development by creating an account on GitHub.
A curated directory of open-source AI agent skills for Swift and Apple platform development. - twostraws/Swift-Agent-Skills
if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence.
Internal workflows used by Cursor developers for CI, code review, shipping, control-cli, control-ui, verify-this, test reliability, code cleanup, and work…
Build product integrations with AI. Contribute to NangoHQ/nango development by creating an account on GitHub.
AgentScope is an open-source multi-agent platform for building LLM-powered agent applications with drag-and-drop workflows, runtime management, and Spark Design system.
A lightweight, powerful framework for multi-agent workflows and voice agents - openai/openai-agents-js
Light, fluffy, and always free - The AWS Local Emulator alternative - floci-io/floci
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy’s observations on LLM coding pitfalls. - multica-ai/andrej-karpathy-skills
Paradigm and Tempo open source Centaur, a Slack-native multiplayer, self-hosted and secure agent for investing, building, and researching.
Vane is an AI-powered answering engine. Contribute to ItzCrazyKns/Vane development by creating an account on GitHub.
Learn how Anthropic’s self-hosted sandboxes for Claude Managed Agents allow you to outsource the reasoning while keeping the code execution on your infrastructure. Discover the benefits of OpenShell, an open source sandbox runtime for AI agents, started by NVIDIA where Red Hat is an active contributor.
