News
Updates, product notes and practical coverage for AI platforms and operators.
AWS has published a reusable architecture for hosting OpenClaw on Amazon Bedrock AgentCore with persistent memory, task-based model routing, skills and serverless infrastructure. The practical deployment guide shows how to isolate user context, survive runtime restarts, control operating cost and degrade gracefully when memory retrieval fails.
OpenClaw has integrated Tencent’s AI-Infra-Guard into ClawScan, adding a second independent scanner to every ClawHub skill and plugin review. The combined process uses an AI judge and a public benchmark, with OpenClaw reporting 98.6 per cent correct classification of malicious cases while establishing a feedback loop for future improvements.
OpenClaw announced an open-source Enterprise control plane on 29 September for persistent agents in sensitive environments. It adds multi-tenancy, governance and security boundaries while keeping core components replaceable. The project is still being developed ahead of version 1.0, and OpenClaw recommends internal pilot workloads rather than treating the current release as finished enterprise infrastructure.
OpenClaw has detailed upstream work by Microsoft contributors, including policy-conformance checks, native Windows chat and approvals, sandbox integration, routing tests, secret redaction and reliability fixes. The 25 September post accompanies Microsoft’s Autopilot announcement but concerns improvements available to the wider OpenClaw project. Operators should test each capability and distinguish individual contributions from guaranteed Autopilot features.
OpenClaw is developing an opt-in, plugin-first interface for fast decision models that make narrow choices such as tool filtering and reply routing. Its maintainers describe a shared API and an early TypeSafe adapter, while stressing that provider packages and proposed uses are not all shipped. Existing agents continue unchanged unless configured for the new capability.
OpenClaw has published results of a Trail of Bits security audit supported by OpenAI’s Patch the Planet initiative. It says 23 vulnerabilities were confirmed among 24 severity-rated reports, with no critical and two high-severity findings, and that every actionable issue is fixed. Users should still update to a stable release and review their agent permissions.
OpenClaw has detailed work to make upgrades less disruptive, including preparing updates while the existing gateway remains available and improving issue reporting. The maintainer account describes progress, not perfect reliability. Supporting documentation makes an important distinction: restoring an earlier package cannot automatically reverse database migrations or replace a verified backup.
OpenClaw has introduced a central security page bringing together advisories, vulnerability-reporting guidance and ongoing defensive work. The announcement also points to published skill-scan research. Its status information has a defined scope and review date, so the page should be read as a transparency resource rather than a blanket safety guarantee.
OpenClaw has added a guided macOS installer and automatic detection of existing AI access. On supported Windows NVIDIA RTX PCs, onboarding can now suggest and manage local 30B-class models, aiming to reduce setup friction while keeping device permissions visible and configurable. Users should still verify model sources, storage requirements and agent permissions before deployment.
OpenClaw has released version 2.0, a major update that simplifies first-time setup, rebuilds its browser app and adds shared cloud sessions. The open-source personal AI runtime says the release also spans messaging, memory, skills, models, automations, plugins, security and a large collection of stability fixes.