LLMD: Run LLM Inference on Any Chip, One Docker Tag
ZML released LLMD, a free LLM inference server that runs LLaMA, Gemma, Qwen, and Mistral on NVIDIA, AMD, Google TPU, Intel, and Apple ...
Gleam v1.17 and v1.18: Two Fixes That Matter
Gleam dropped v1.17 and v1.18 on July 29. The language server finally navigates record fields. ...
OpenAI Codex Security CLI: Open Source With One Catch
OpenAI Codex Security CLI is now open source on npm. Here is what the AI-powered ...
JEP 540: Java Gets a Built-In JSON API, No Jackson Needed
JEP 540 adds native JSON parsing to the JDK. No Jackson, no dependencies. Here is ...
Zed Agent Sandboxing: Enable It Before Your AI Agent Runs rm -rf
Zed shipped OS-level agent sandboxing in its preview channel last week, and the timing is ...
Nono: Sandbox Your AI Coding Agent Without a VM
Every AI coding agent running on your machine — Claude Code, GitHub Copilot, Codex, Cursor — inherits your full user-level permissions. That means ...
GitHub Stacked PRs Now Public: No Waitlist, No Rebase Hell
GitHub stacked pull requests moved to public preview on July 30. One CLI install, no ...
Claude Opus 5: Half the Price, Better Benchmarks Than Fable 5
Anthropic released Claude Opus 5 on July 24, and the benchmark numbers tell a more ...
Hallmark: Stop AI-Generated UI Slop in One Command
Hallmark is an open-source design skill for Claude Code and Cursor that just hit 12K ...
MCP 2026-07-28 Spec: What Breaks and How to Migrate
The MCP 2026-07-28 spec removes sessions, kills the initialize handshake, and deprecates five features. Here ...