VonHeikemen/lsp-zero.nvim: A starting point to setup some lsp related features in neovim.
A starting point to setup some lsp related features in neovim. - VonHeikemen/lsp-zero.nvim
Auto mode is now the default in Claude Code for Pro, Max, and Team plans | Claude by Anthropic
Claude Code will soon run auto mode by default for Pro, Max, and Team plans, enabling longer-running autonomous work, and catching more dangerous commands.
1jehuang/jcode: The most RAM efficient harness
The most RAM efficient harness. Contribute to 1jehuang/jcode development by creating an account on GitHub.
The Pulse: Quitting Spotify Podcasts over reliability
Spotify’s podcast platform has become chronically unreliable since the company’s leadership started boasting about AI adoption. Competitors haven’t had similar issues, so I offboarded from Spotify.
Unpacking ChatGPT Work: the Agent for a Billion Users
An external reconstruction of how Memory, Proactivity, Scheduling, Browser Use, Plugins, Skills and Tools work in the new ChatGPT Work.
OmniWM Documentation
MacOS Niri and Hyprland inspired tiling window manager that’s developer signed and notorized (safe for managed enterprise environments). Aiming for parity and extra innovation.
BarutSRB/OmniWM: MacOS Niri and Hyprland inspired tiling window manager that's developer signed and notorized (safe for managed enterprise environments). Aiming for parity and extra innovation.
MacOS Niri and Hyprland inspired tiling window manager that's developer signed and notorized (safe for managed enterprise environments). Aiming for parity and extra innovation. - BarutSRB/OmniWM
Blue Oak Model License 1.0.0
Humans missed 1 in 3 threats approving AI agent commands across 40,000 plays
Results from AI agent permission game: which attacks beat human reviewers, and which safe commands got blocked instead.
petergyang/human-review: A visual tool to edit HTML and Markdown files, leave comments like a Google Doc, and send feedback to your AI agent. Works inside your favorite AI harness.
A visual tool to edit HTML and Markdown files, leave comments like a Google Doc, and send feedback to your AI agent. Works inside your favorite AI harness. - petergyang/human-review
denoland/celld: self-hosted, distributed Durable Objects
self-hosted, distributed Durable Objects. Contribute to denoland/celld development by creating an account on GitHub.
celld — Durable Objects, self-hosted
The Durable Objects programming model on machines you own. Addressable, single-writer actors with a private SQLite database, state in your own bucket. Open source, ~9x cheaper than Durable Objects for resident agents.
jurplel/InstantSpaceSwitcher: Native space switching on macOS with no animation
Native space switching on macOS with no animation. Contribute to jurplel/InstantSpaceSwitcher development by creating an account on GitHub.
Instant Space Switching for macOS
Space Rabbit removes the macOS Spaces slide animation. Zero delay, zero config.
Tahul/space-rabbit: Space Rabbit removes animations when switching macOS Spaces. Reclaim hours of your time every month!
Space Rabbit removes animations when switching macOS Spaces. Reclaim hours of your time every month! - Tahul/space-rabbit
Marcos Hernanz on X: "After doing ~60B tokens, this is my full AGENTS.md https://t.co/VVXIwtSAcO" / X
firecrawl/anydoc: Convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF to clean Markdown. Built in Rust, with Node.js and Python bindings.
Convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF to clean Markdown. Built in Rust, with Node.js and Python bindings. - firecrawl/anydoc
boldsoftware/meat: meat.dev
meat.dev. Contribute to boldsoftware/meat development by creating an account on GitHub.
algal/pi-openai-server-compaction
Contribute to algal/pi-openai-server-compaction development by creating an account on GitHub.
Everyone is building LLM routers, we deprecated ours
We don't believe in model routing anymore. For most use cases, sticking to a single battle-tested model is the best thing you can do.
オリジナルのフルグラフィックTシャツ（全面プリント）を安く作れるTMIX
【送料無料】オリジナルのフルグラフィックTシャツ（全面プリントTシャツ）を制作するならTMIX（ティーミックス）！1枚から印刷できて安い♪ イベント物販からクラスTシャツまで、幅広い用途で活躍。デザインサポートあり！
jdx on X: "does anyone else prefer having super vanilla AGENTS.md, not use skills, basically no agent configuration? I'm considering removing most of what's in these in my projects. Agents don't need it and it's mostly noise. I feel it probably makes agents behave worse." / X
I'm considering removing most of what's in these in my projects. Agents don't need it and it's mostly noise. I feel it probably makes agents behave worse.
How to protect a Rails app from AI slop code
AI writes confident Rails code that quietly breaks production standards. Build a quality workflow that catches it: Lefthook gates, Strong Migrations as a hard line, N+1 detection with Prosopite, database checks in layers, and CI that mirrors local hooks.
SleeperGem: RubyGems supply chain attack targets dormant maintainer accounts
SleeperGem: two dormant RubyGems maintainer accounts were hijacked to inject malware into trusted gems, one with over 500,000 total downloads
The Metaphysics of Vibe Coding (or the Absence of It) - Julian Rubisch
Thoughts on how an old philosophical debate resurfaces in the agentic coding discussion. Is code really disposable or is it an essential artifact for thinking? How does the relationship we have to the coded representations shape our decision-making process?
owainlewis/push: A secure, stable, and lightweight alternative to OpenClaw and Hermes.
A secure, stable, and lightweight alternative to OpenClaw and Hermes. - owainlewis/push
Don't Ship Skills Without Evals — Philipp Schmid, Google DeepMind
There are thousands of agent skills. Almost none of them are tested. They get vibe-checked with two manual runs, maybe a thumbs-up from a colleague, then shi...
Automate Tech Debt Audits with Claude Code | FastRuby.io
How to write a Claude Code skill that automates tech debt audits for Rails applications, combining security, dependencies, coverage, and complexity.
Better Stack - 30x cheaper than Datadog, Exceptional support
AI SRE and MCP server, incident management, on-call, logs, metrics, traces, and error tracking. 7,000+ happy customers. 60-day money back guarantee.
evilmartians/agent-skills: Production-grade Agent Skills from Evil Martians — drop-in expertise for your AI coding agent
Production-grade Agent Skills from Evil Martians — drop-in expertise for your AI coding agent - evilmartians/agent-skills