OpenClaw v2026.3.24 brings Teams overhaul, skills UI refresh, and Open WebUI support

ByIvan Jenic

OpenClaw shipped v2026.3.24 two days after its previous release. The new version brings OpenWebUI supprt, better Microsoft Teams integration, and more.

openclaw logo

OpenClaw released version 2026.3.24 today, just two days after the security-heavy v2026.3.22. No breaking changes this time — focused on new functionality and fixes.

The headline addition for many users will be expanded OpenAI API compatibility, which now lets you talk to OpenClaw sub-agents directly through Open WebUI. The update also adds /v1/models and /v1/embeddings endpoints for broader RAG and client support.

Microsoft Teams got a full overhaul. The integration now runs on the official Teams SDK with AI-native UX including streaming replies, welcome cards with prompt starters, typing indicators, and native AI labeling. Message edit and delete support is included too.

The skills interface received a meaningful refresh.

  • Status filters: New tabs for All, Ready, Needs Setup, and Disabled with item counts.
  • One-click installs: Bundled skills including coding-agent, GitHub issues, Trello, and weather now ship with install recipes for missing dependencies.
  • Tools visibility: The /tools command now shows what the current agent can actually use in real time.

Other changes worth knowing about:

  • Slack: Interactive reply buttons restored with rich reply parity for direct deliveries.
  • Discord: Auto-created threads can now be named asynchronously using LLM-generated titles.
  • Container support: New --container flag for running OpenClaw commands inside Docker or Podman.

On the fixes side, a bug where one broken channel blocked all other channels from starting on boot is now resolved. WhatsApp group echo suppression, Telegram forum topic routing, and Docker fresh install failures also got patches.

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