OpenClaw Releases Version Update with New Inference and Media Generation Features

2026-04-08 13:33:52

Abstract generation in progress

On April 8, OpenClaw released version 2026.4.7, introducing several key new features: · OpenClaw Inference Functionality: Serving as a unified hub for inference workflows, it supports provider-driven inference capabilities across models, media, networks, and embedded tasks. · Tool/Media Generation: Default support for automatic failover across certified providers (images, music, videos), maintaining original generation intent during provider switches; automatically mapping parameters such as size, aspect ratio, resolution, and duration to the closest supported options, and opening a provider capability query interface, along with new mode-aware video-to-video support. · Memory/Wiki: Restoration of the built-in memory-wiki tech stack, including plugins, command-line tools, synchronization/query/application toolchains, memory host integration, structured declarations and evidence fields, and compiled summary retrieval. · Plugins/Webhook: Introduction of a built-in webhook inbound plugin, supporting external automation systems to create and drive binding task flows through independently shared key endpoints across various routes. · Support for Arcee, Gemma 4, and Ollama visual models.

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.