OpenClaw v2026.10.10

OpenClaw v2026.10.10 adds a Details panel beside the chat, an experimental Advisor that can suggest course corrections during a task, a split speech mode for browser Talk, and event-triggered automations from connected MCP servers.

Why it matters

For people running OpenClaw as a self-hosted personal assistant. This release lets the agent work in folders on another paired computer, lets ChatGPT or Claude reach your OpenClaw conversations through an opt-in relay, and starts automations from events instead of timers.

What's new

• Chat Details gathers session information, task progress, pull requests and automations into a panel that opens beside wide conversations.
• Advisor (experimental, off by default under Settings, System, Labs) reviews an agent's ongoing work and may suggest a correction when it spots a clear wrong turn; the notes say it uses extra model calls and can miss problems.
• Split speech mode for browser Talk uses your normal chat model with separately configured transcription and speech services; it has no realtime voice switching or camera input.
• Agents can now work directly in an existing folder on another computer paired with OpenClaw, controlled by that computer's nodeHost.workerRuns.folders setting.
• Opt-in MCP Relay connects ChatGPT or Claude to your OpenClaw conversations without opening a public Gateway port, and automations can start when a connected MCP server reports an event (experimental, OpenAI webhook profile only).

Taken from the project's own release notes. Claims about speed or accuracy are the maker's unless stated otherwise.

Worth knowing: The release notes warn that the MCP Relay can read content passing through it, so grant it only to apps you trust, and that MCP event automations need a public HTTPS callback route.

Quick facts

Links

• Official site: https://openclaw.ai
• Repository: https://github.com/openclaw/openclaw
• Release notes: https://github.com/openclaw/openclaw/releases/tag/v2026.10.10
• Docs: https://docs.openclaw.ai/releases/2026.10.10

Related ranking

See how established tools compare in Best AI Agents That Do Tasks for You. New releases aren't scored until we review them against the rubric.

What we couldn't verify

• quick_facts.platform (carried from earlier releases)
• quick_facts.language (Node.js version requirement not rechecked)

Checked 2026-11-03 from the release notes's own pages. Prices and star counts change, so confirm on the official site. Listing here is not a ranking or an endorsement.