OpenClaw 2026.4.12-beta.1 Beta Release
💡Beta fixes plugin security, memory recall, dreaming—key for stable AI agents
⚡ 30-Second TL;DR
What Changed
Narrowed plugin activation to manifest-declared needs preserving trust boundaries (#65120)
Why It Matters
This beta strengthens OpenClaw's plugin security and memory reliability, reducing runtime errors for AI agent workflows. Developers benefit from fewer self-promotions in dreaming and consistent recall, streamlining production use.
What To Do Next
Upgrade to openclaw 2026.4.12-beta.1 via CLI and test QMD recall in your memory-backed agents.
Key Points
- •Narrowed plugin activation to manifest-declared needs preserving trust boundaries (#65120)
- •Default QMD recall now searches for better memory telemetry predictability (#65068)
- •CLI self-update respawn fix prevents stale import failures (#65471)
- •Dreaming enhancements consume heartbeats once and harden narrative cleanup (#65320)
- •Unicode preservation in wiki slugs and filename caps (#64742)
Weekly AI Recap
Read this week's curated digest of top AI events →
👉Related Updates
AI-curated news aggregator. All content rights belong to original publishers.
Original source: OpenClaw (GitHub Releases) ↗
This is a summary, not the original. Read the source, or get the weekly briefing.
The weekly digest
One email a week. Unsubscribe anytime.