OpenClaw 2.0 Makes Sessions Portable, Credentials Private, and Plugins Explicit
OpenClaw 2.0 ships portable sessions, private credential requests, recurring approvals, explicit plugin provenance, stronger memory, and a rebuilt operator experience.
OpenClaw 2026.9.1 Beta 1 Brings Restart-Safe Agents and Leaner Context
Restart-safe runs, visible worker failure, safer config writes, context control, durable memory, and a local agent model define today's OpenClaw briefing.
OpenClaw 2026.8.1 Beta 3: Secrets, Codex, and Trust at Scale
OpenClaw 2026.8.1 beta 3 binds secret egress, expands Codex operations, and confronts trust at scale across contributors and agent infrastructure.
OpenClaw Enters the Sandbox-and-Agent-Company Era
OpenClaw’s latest beta meets policy sandboxes, container-first assistants, package controls, and a new agent-company orchestration layer.
OpenClaw Codex Harness Clarifies the Agent Control Plane
OpenClaw’s official Codex harness defines runtime ownership, remote execution, secret boundaries, and a growing ecosystem of managed agent infrastructure.
OpenClaw 2026.8.1 Beta 3 Connects Models, Browsers, and Durable Channels
OpenClaw 2026.8.1-beta.3 coordinates GPT-5.6 runtimes, paired-browser automation, durable channel ingress, verified backups, and a broader agent ecosystem.
OpenClaw 2026.8.1 Beta Secures Secrets as Codex and ClawHub Broaden the Stack
Host-bound secrets lead a practical OpenClaw briefing on Codex runtime control, verified backups, safer package discovery, and multi-agent operations.
OpenClaw 2026.8.1 Beta Binds Secrets to Hosts as Windows Companion Expands
OpenClaw 2026.8.1 beta adds host-bound secret egress, verified SQLite snapshots, safer plugin provenance, atomic runtime switching, and broader device operations.
OpenClaw Codex Harness Draws Remote Boundaries as Agent Teams Enter Slack
OpenClaw clarifies remote Codex execution and attachment boundaries while beta fixes, NanoClaw Slack teams, Paperclip, and OpenHarness push agent operations forward.
OpenClaw Beta Expands GPT-5.6 and GLM Routing as Caveman Tightens Safety
OpenClaw broadens model routing across GPT-5.6 and GLM while Caveman v2.2.0 fixes installer races, unsafe temp handling, and destructive rewrite validation.
OpenClaw 2026.8.1 Beta Hardens Secrets, Backups, and Agent Operations
OpenClaw 2026.8.1-beta.2 binds secret egress to destination hosts, adds verified SQLite snapshots, scopes external coding sessions, and sharpens plugin provenance.
OpenClaw 2026.8.1 Beta Binds Secrets, Verifies Backups, and Broadens Agent Interoperability
A prerelease built around operational boundaries: destination-bound secrets, verified data recovery, explicit plugin trust, and a widening multi-agent ecosystem.
OpenClaw Fixes Gateway Stalls, TLS Pin Drift, and False-Green Automation
Fresh merged changes target the operational failures that make healthy-looking agent systems lie: stalled readiness, divergent TLS identity, reordered streams, and false success exits.
OpenClaw Windows Companion, ClawHub Packages, and Agent Orchestration Move Forward
A native Windows control surface and a broader package registry meet an ecosystem increasingly focused on migration, budgets, and accountable agent work.
OpenClaw 2026.8.1 Beta 2 Adds Secret Host Binding, SQLite Backups, and Safer Plugins
The newest OpenClaw beta tightens secret egress, adds database snapshots, improves plugin provenance, and advances a broader local-agent operations ecosystem.
Page 3 of 16