Pizza Bot (Apache-2.0, a community project rather than an AWS service) runs scheduled or webhook-triggered agent work in the background, delegates to specialist agents, and pauses in an Action queue for your approval before consequential steps. It supports multiple model providers, MCP servers, and Agent Skills, and keeps threads, checkpoints, and logs in a local folder with credentials in the OS secret store.
Curie (Apache 2.0, v0.12.0) takes a Claude Code format plugin bundle (skills, tools, MCP) and runs the same snapshot as a single container, a local Docker Compose stack, or a Kubernetes release, with traces, evals, budgets, and deploys on git push . Slack is the first channel, with email and Teams next; models can be Anthropic, OpenRouter, or local Ollama, and curie try gets a first reply without credentials…
ChatGPT's new Code Review plugin lets Codex read and help review GitHub PRs (GitLab MRs in preview), but anything typed in the Summary or Changes panes goes live on the PR immediately, before you hit Submit review. Keep drafts in chat, and check the model's file and line references before posting…
Lovable found an unauthenticated reflected XSS (GHSA qx66 fv34 fjm8) in TanStack Start server functions: a crafted link runs attacker JS on your app's origin with the visitor's access, affecting versions from 1.143.12. Upgrade to @tanstack/react start 1.168.60+ (or start server core 1.169.39+) and redeploy, since a local update alone doesn't patch a live app…
Taylor Wilsdon’s Google Workspace MCP 2.0 (Oct 2) moves to FastMCP 4 and MCP Python SDK v2 for sessionless 2026 07 28 replicas—12 Google services, 119 tools ( uvx workspace mcp@latest ). Patch 2.0.1 (Oct 4) fixes FastMCP 4 OAuth challenges to advertise tool scopes, and adds Docs tab id reads plus Sheets cell anchored comments…
Starting October 9, Gemini app free users are limited to Flash Lite (no Flash or Pro), and AI Plus ($4.99) keeps Flash Lite and Flash but loses Pro. AI Pro and Ultra keep all models; Pro also gains Deep Think, and the app is adding low/medium/high effort levels…
Spotted something we missed? Start a thread.