OpenClaw v2026.3.28 brings xAI search, MiniMax image generation, and plugin approval system

ByIvan Jenic

OpenClaw v2026.3.28 ships with 71 contributors and first-class xAI search, MiniMax image generation, and a new plugin approval system.

openclaw logo

OpenClaw released v2026.3.28 with contributions from 71 developers. No major breaking changes, but a substantial list of new functionality and fixes.

The most notable additions:

  • xAI search: Grok now has first-class x_search integration via the Responses API, with optional setup during onboarding. No manual plugin toggles required.
  • MiniMax image generation: The Image-01 model is now available for image generation and image-to-image editing with aspect ratio control.
  • Plugin approval system: Plugins can now pause tool execution mid-run and ask the user for approval via Telegram buttons, Discord interactions, the exec overlay, or the /approve command on any channel.
  • ACP channel expansion: /acp spawn codex --bind here now works in Discord, BlueBubbles, and iMessage, turning any of those chats into a Codex workspace without creating a child thread.
  • Gemini CLI backend: Added alongside the existing Claude and Codex CLI backends.
  • Rate limit fix: A 429 error on one model no longer blocks all models on the same auth profile. Cooldowns are now scoped per model.

Two breaking changes worth checking before updating.

  • Qwen OAuth removed: The deprecated qwen-portal-auth integration is gone. Migrate to Model Studio with openclaw onboard --auth-choice modelstudio-api-key.
  • Old config migrations dropped: Automatic migration for configs older than two months is no longer supported. Very old legacy keys will now fail validation.

Notable fixes include a WhatsApp self-chat infinite echo loop, Telegram message splitting at word boundaries, Mistral API 422 errors, and Discord gateway shutdown crashes.

Source: GitHub / OpenClaw

RunPod
RunPod

If you need on-demand GPUs for training, fine-tuning, inference, or running open-source models, give RunPod a try.

  • Available hardware: H100, H200, A100, L40S, RTX 4090, RTX 5090, and 30+ more
  • Cost: significantly cheaper than AWS or GCP, billed per second, no contracts
  • Setup: spins up in under a minute, 30+ regions worldwide
Try RunPod →
Affiliate disclosure: We may earn a commission if you sign up via our link, at no extra cost to you.
Efficienist Newsletter

Get the core business tech news delivered straight to your inbox. We track AI, automation, SaaS, and cybersecurity so you don't have to.

Just read what you want, and be done with it.

Read Next