Uncategorized

security shield mesh — hardening header

OpenClaw 2026.4.20: Smarter Prompts, Tiered Pricing, Session Health

OpenClaw 2026.4.20 strengthens the default system prompt, adds tiered model pricing, and enforces session maintenance caps to keep your gateway healthy. Highlights đź“ť Smarter Default Prompts The default system prompt and GPT-5 overlay have been strengthened with clearer completion bias, live-state checks, weak-result recovery, and verification-before-final guidance. Your agent will be more decisive and less

OpenClaw 2026.4.20: Smarter Prompts, Tiered Pricing, Session Health Read More »

server room corridor — release header

OpenClaw 2026.4.18: Claude Opus 4.7 xHigh Reasoning, Settings Overhaul, Stability Fixes

OpenClaw 2026.4.18 adds xHigh reasoning support for Claude Opus 4.7, overhauls the settings experience, and ships important stability fixes. What’s New 🧠 Claude Opus 4.7 xHigh Reasoning Anthropic’s most capable model now supports the xHigh reasoning effort level, giving your agent the deepest possible thinking for complex tasks. This is separate from adaptive thinking and

OpenClaw 2026.4.18: Claude Opus 4.7 xHigh Reasoning, Settings Overhaul, Stability Fixes Read More »

OpenClaw 2026.4.15: Claude Opus 4.7 Default, Gemini TTS, Model Auth Dashboard

OpenClaw 2026.4.15 ships with Claude Opus 4.7 as the default Anthropic model, Gemini-powered text-to-speech, and a beautiful new Model Auth dashboard in the Control UI. Highlights 🤖 Claude Opus 4.7 Default All Anthropic selections, opus aliases, Claude CLI defaults, and bundled image understanding now default to Claude Opus 4.7 — Anthropic’s most capable model. 🔊

OpenClaw 2026.4.15: Claude Opus 4.7 Default, Gemini TTS, Model Auth Dashboard Read More »

OpenClaw 2026.4.14: GPT-5.4 Pro, Telegram Forum Topics, Major Security Hardening

OpenClaw 2026.4.14 brings forward-compatibility for GPT-5.4 Pro, human-readable Telegram forum topics, and a wave of security hardening across the platform. What’s New 🧠 GPT-5.4 Pro Forward Compatibility OpenClaw now supports GPT-5.4 Pro including Codex pricing/limits and list/status visibility before the upstream catalog catches up. đź’¬ Telegram Forum Topics Telegram forum topics now surface human topic

OpenClaw 2026.4.14: GPT-5.4 Pro, Telegram Forum Topics, Major Security Hardening Read More »

OpenClaw 4.10 & 4.11 — What’s New and Why You Should Upgrade

Two releases in 48 hours. That’s the pace OpenClaw is setting right now — and if you’re running an AI assistant for your business, you need to know what just changed. On April 11, 2026, OpenClaw shipped version 2026.4.10 — a 17-feature, 20+ fix release that rewrites how the platform handles memory, coding agents, and

OpenClaw 4.10 & 4.11 — What’s New and Why You Should Upgrade Read More »

OpenClaw 2026.4.12: Active Memory, LM Studio Support, Codex Provider & More

OpenClaw 2026.4.12 is a massive update packed with new features that fundamentally expand what your agent can do. This is one of the most important releases of the month. Highlights 🧠 Active Memory Plugin The new Active Memory plugin gives OpenClaw a dedicated memory sub-agent that runs automatically before each reply. Your agent now proactively

OpenClaw 2026.4.12: Active Memory, LM Studio Support, Codex Provider & More Read More »

Scroll to Top