OpenClaw Adds xAI Multimodal Tools and Local TUI for Secure Debugging
AI Assistant
Audio Generation
Image Generation
LLM
AI Agent
Multimodal
Performance
OpenClaw, an open-source AI assistant that connects models to messaging platforms, released version 2026.4.22 with full xAI integration. This update adds image generation, text-to-speech, and realtime transcription (converting audio to text instantly) for voice calls. It also introduces Tencent Hy3 and a local terminal interface for debugging.
This release addresses the token tax of autonomous agents by bundling Tokenjuice, a plugin that compacts verbose tool outputs. It extends the pattern of optimizing context seen in recent updates. Dynamic model registration allows users to swap providers from chat without restarting the gateway, reducing downtime during complex multi-model experiments.
You can now use /models add to register providers or run the local terminal interface to test plugins without a gateway. The update is available on GitHub and includes a diagnostics export. Linux users benefit from memory protections that prevent the kernel from killing the main process during inference.
Frequently asked questions
- What is the new Local TUI mode in OpenClaw?
- The Local TUI mode allows users to run terminal-based chats directly without starting the full OpenClaw Gateway. This mode is designed for quick local sessions and offline debugging while still enforcing plugin approval gates, ensuring that autonomous tools cannot execute sensitive actions without explicit user permission during the terminal session.
- How does the Tokenjuice plugin work in OpenClaw?
- Tokenjuice is an opt-in plugin that reduces the number of tokens consumed during agentic workflows. It works by compacting the results of noisy tool calls, specifically those involving terminal execution and bash commands. By shrinking these outputs before they are sent back to the model, it helps lower inference costs and prevents context window overflow.
- What xAI features were added to OpenClaw version 2026.4.22?
- This update introduces full support for xAI multimodal tools, including image generation via grok-imagine and text-to-speech with six distinct live voices. It also adds audio transcription and realtime transcription for voice calls. These tools allow the assistant to generate visuals, speak in various formats like MP3 or WAV, and process live audio streams.
- How do you add new models to OpenClaw without restarting the gateway?
- Users can now register new models directly from the chat interface using the /models add command followed by the provider and model ID. This feature allows the assistant to use the new model immediately without requiring a full restart of the OpenClaw Gateway, simplifying the process of testing different large language models or switching providers.
- What security improvements were made to the OpenClaw sandbox?
- The OpenShell sandbox received critical hardening to prevent symlink attacks that could allow an agent to read files outside the intended directory. By pinning file reads to verified descriptors and checking the identity of parent directories, the system ensures that malicious symlink swaps cannot redirect sandbox operations to sensitive host files on the underlying machine.
