OpenClaw releases version 2026.4.7, introducing new features such as persistent knowledge layers and more.

Deep Tide TechFlow message, April 08, according to an official announcement, OpenClaw released the 2026.4.7 version update, adding multiple core features: first, it launched a headless inference core, openclaw infer, to unify the CLI interface to support multimodal inference including models, images, audio, TTS, video, web pages, and embeddings; second, it rolled out a Webhook-driven TaskFlow, allowing external systems to create and run task flows through a shared secret endpoint; third, it published a memory-wiki persistent knowledge layer, supporting structured knowledge declarations and evidence management, contradiction detection and freshness tracking, and optionally compatible with the Obsidian vault format. In addition, this update also added support for Arcee, Gemma 4, and Ollama vision models.

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