Stop AI Coding Agents From Deleting Your Files

Stop AI Coding Agents From Deleting Your Files

A string of incidents shows Claude Code and OpenAI Codex accidentally deleting files, dropping database tables, and overwriting work. None were malicious. Here are five guardrails that stop it.

GPT-5.6 Codex Deleted User Files: How to Stay Safe

GPT-5.6 Codex Deleted User Files: How to Stay Safe

OpenAI confirmed that GPT-5.6 Codex, its flagship coding model, deleted files from users home directories in a handful of documented cases. If you run Codex in your build workflow, the fix is about permissions, and you can apply it today.

Figmaboy: A Local-First Figma Clone With Codex Built In

Figmaboy: A Local-First Figma Clone With Codex Built In

Figmaboy is an open-source, local-first Figma clone with OpenAI's Codex CLI built directly into the canvas. Instead of generating flat images, its MCP server lets Codex inspect and edit real frames, layers, and components in your live document.

GitHub Copilot CLI Gets Real Code Intelligence

GitHub Copilot CLI Gets Real Code Intelligence

GitHub Copilot CLI can now use Language Server Protocol servers for real code intelligence, replacing text heuristics with precise, type-aware answers across 14 languages.

Zerostack: A Rust Coding Agent With 8MB RAM

Zerostack: A Rust Coding Agent With 8MB RAM

Zerostack is a pure Rust coding agent that launched May 16, 2026, running in 8MB of RAM compared to 300MB for JavaScript-based alternatives like Opencode.

OpenAI Codex Auto-Imports CLAUDE.md, Adds Codex Pets

OpenAI Codex Auto-Imports CLAUDE.md, Adds Codex Pets

OpenAI shipped a May 2 Codex update that auto-imports Claude Code CLAUDE.md and other rival agent configs into AGENTS.md, plus eight animated Codex Pets that float over your screen as ambient status indicators.

IBM Granite 4.1: Dense LLMs Walk Back the MoE Bet

IBM Granite 4.1: Dense LLMs Walk Back the MoE Bet

IBM released Granite 4.1 on April 29, 2026 with dense decoder-only 3B, 8B, and 30B Apache 2.0 LLMs that walk back the Granite 4.0 MoE bet. The 8B dense beats the 32B-A9B MoE on most benchmarks. 128K production context, 512K extension.

Cursor Launches SDK for Programmatic Coding Agents

Cursor Launches SDK for Programmatic Coding Agents

Cursor released a TypeScript SDK on April 29, 2026 that lets developers build and deploy AI coding agents programmatically, embedding the same runtime that powers Cursor into their own products and pipelines.

Mistral Workflows: Durable Orchestration for AI Agents

Mistral Workflows: Durable Orchestration for AI Agents

Mistral launched Workflows in public preview on April 28, 2026. Built on Temporal durable execution, the platform brings replay-able workflows, HITL approval gates, and audit trails to AI orchestration.

Claude's Official Blender Connector: Setup and Workflow

Claude's Official Blender Connector: Setup and Workflow

Anthropic's official Claude Blender connector shipped April 28, 2026. Drag-and-drop install, Free-tier eligible, scene-graph aware. The verified setup, the four workflows Anthropic has demoed, and the limits to know.

Poolside Releases Laguna M.1 and Open-Weight XS.2

Poolside Releases Laguna M.1 and Open-Weight XS.2

Poolside released the first two models in its Laguna family on April 28: a 225B-parameter flagship called M.1 and an open-weight 33B model called XS.2 under Apache 2.0. Both are pitched at agentic, long-horizon coding work.

Free Weekly Newsletter

Stay ahead of Creative AI

Join creators getting the latest AI tools, model releases, and workflow tips delivered weekly.

No spam. Unsubscribe anytime.