Just saw OpenClaw update to the new version (v2026.4.12), and there are some great features. Previously, to use LM Studio, you had to configure it manually. Now it automatically detects models, preloads streams, and even supports local embedding vector search. Just configure it and you can use it right away.



Even better, the Feishu bot now only needs you to scan a QR code—no need to go into Feishu’s open platform to configure callbacks manually anymore. In the past, it took a lot of effort, but now it’s much more convenient for businesses.

There are also other improvements: optimized runtime for GPT-5, and separated prompt logic and retry logic so long-term tasks are more stable. The Active Memory plugin has also been improved, with more accurate search modes. They also fixed three security vulnerabilities, detected with AI assistance.

Is anyone using OpenClaw? Is this update useful?
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pin