TechFlow News: On April 8, according to the official announcement, OpenClaw released version 2026.4.7, introducing several core features: First, it launched the headless inference hub “openclaw infer,” which provides a unified CLI interface supporting multimodal inference—including models, images, audio, text-to-speech (TTS), video, web content, and embeddings. Second, it introduced Webhook-driven TaskFlow, enabling external systems to create and trigger task flows via shared-key endpoints. Third, it released the memory-wiki persistent knowledge layer, supporting structured knowledge declaration and evidence management, contradiction detection, and freshness tracking—and optionally compatible with the Obsidian knowledge base format. Additionally, this update adds support for Arcee, Gemma 4, and Ollama vision models.
Add to Favorites
Share to Social Media





