OpenClaw· Updated
OpenClaw v2026.4.15 adds support for Anthropic's Claude Opus 4.7 and high-quality voice output via Gemini Text-to-Speech. The update also optimizes local model performance by stripping heavy default tools to reduce prompt overhead on weaker hardware.
v2026.4.15 with support for Anthropic's Claude Opus 4.7. The update integrates Google's Gemini Text-to-Speech (AI-generated voice output) and adds cloud storage support for LanceDB memory indexes, allowing durable assistant memory to live on remote object storage.This release reduces prompt overhead on local models by introducing a lean mode that drops heavyweight tools like browsers. By shrinking the system prompt, users running smaller models via Ollama can avoid context-overflow errors (when the input exceeds the model's memory limit) while maintaining core assistant functionality.
You can now monitor provider health through a new Model Auth status card in the Control UI. The update is available as a free download on GitHub for macOS, Linux, and Docker. Security is also tightened with new guards that prevent user-defined tools from mimicking built-in system permissions.
OpenClaw 2026.4.15 🦞 🤖 Anthropic Opus 4.7 support 🗣️ Gemini TTS in bundled 🧠 Slimmer context + bounded memory reads 🔧 Codex transport self-heal, safer tool/media handling ✨ Pile of update/channel fixes Good boring release. https://t.co/jiLmr1Bxep
Every HeadsUpAI update is written based on its original source and reviewed before it's published. Read our editorial standards →