News & Insights
42 ClawDocx posts in News & Insights: OpenClaw and Claude Code guides, tips and analysis, newest first.
Claude Code 2.1.302: the three default changes to check before you upgrade
Claude Code v2.1.302 was tagged on 16 October 2026. Three entries change defaults for scripted, desktop and VS Code sessions rather than adding features.
Claude Code 2.1.319 changes auto mode when telemetry is off, and claude -p now exits 1
Claude Code 2.1.319 stops auto mode falling back to its built-in classifier when telemetry or feature flags are off, and makes claude -p exit 1 on refusal.
Personal Finance in Claude is in beta, and a linked bank is off limits to Claude Code
Anthropic opened Personal Finance in Claude on 5 November 2026: read-only bank access in beta on Pro, Max and Ultra in the US, and no access from Claude Code.
OpenClaw v2026.11.1 is out, and it needs a Gateway restart to apply its certificate change
OpenClaw v2026.11.1 landed on 5 November 2026 and rejects a distrusted certificate root, so restart the Gateway after you update.
OpenClaw v2026.10.10 is out, and upgrading from 2026.10.7 passes two security releases
OpenClaw v2026.10.10 landed on 3 November 2026. If you are still on 2026.10.7, the upgrade also brings the security work from 10.8 and 10.9.
Claude Code 2.1.299 tightens MCP allow rules, MCP redirects and skill file names
Claude Code 2.1.299 shipped on 14 October 2026: MCP allow rules now reach only the server they name, and MCP requests stop following redirects.
A tampered Claude Code extension on Cursor's marketplace installed an SSH backdoor
Cursor says tampered Claude Code extension builds 2.1.312 and 2.1.313 reached its marketplace on 29 October. Here is how to check whether you are affected.
Claude Code 2.1.305 and 2.1.306: the MCP allowlist change to check before you upgrade
Claude Code 2.1.305 stops filtering some managed MCP servers through allowedMcpServers, adds a sandbox namespace switch and fixes a 2.1.304 regression.
Claude Code 2.1.316: fast mode on Opus 4.8 is deprecated, with removal on 30 November 2026
Claude Code 2.1.316 deprecates fast mode on Claude Opus 4.8 and sets removal for 30 November 2026, after which those requests return an error.
Claude Code 2.1.309 and 2.1.310: the sandbox and permission fixes to take now
Claude Code 2.1.309 fixes the sandbox, Bash permission checks, deny rules and hooks on macOS, Linux and Windows. 2.1.310 adds the Monitor tool.
OpenClaw v2026.10.2 fixes a credential redaction leak and the upgrade from 2026.10.1
OpenClaw shipped v2026.10.2 on 12 October 2026. It masks credentials that cross a chunk boundary in tool output and repairs the upgrade from 2026.10.1.
OpenClaw v2026.10.7 is the new stable release, and the docs still say 2026.10.6
OpenClaw shipped v2026.10.7 on 24 October 2026 and GitHub marks it Latest, but the project's own docs index still lists 2026.10.6 as the newest.
OpenClaw v2026.10.6 requires patched Node after the eMudhra CA key compromise
OpenClaw v2026.10.6 is a security patch that now requires Node 24.22.1 or 26.12.1, citing the eMudhra certificate compromise. Upgrade Node first.
OpenClaw v2026.10.1: skill search, MCP Apps and the upgrade steps to run first
OpenClaw v2026.10.1 arrived on 10 October 2026 with installed-skill search, MCP Apps beside chat and external backups. Check the upgrade steps first.
Claude Code 2.1.304: Code Review levels, mod controls and skill hook caps
Claude Code 2.1.304 adds Quick, Standard and Deep levels to Code Review, two new mod tool.check fields, and per-source caps on skill hooks.
Claude API OpenTelemetry tracing: what the beta exports and how to turn it on
Anthropic launched OpenTelemetry export for the Claude API in beta on 14 October 2026. What the spans carry, the two setup paths, and the limits.
Anthropic's 2026 Usage Policy update: what changes for people building agents
Anthropic published its 2026 Usage Policy on 8 October, effective 12 November. The sections that change what an agent may do, and what stays the same.
Claude Code now runs mods: what they change and what they can reach
Anthropic shipped mods in Claude Code v2.1.287 on 1 October 2026. They run inside the agent with your permissions, unsandboxed, and here is what they reach.
Anthropic launches Claude Marketplace: connectors, plugins, agents and partners
Anthropic opened the Claude Marketplace on 23 September 2026, with over 2,000 connectors and plugins, agents you buy with committed spend, and service partners.
OpenAI agent accessed an Australian Medicare portal: what happened and what it means
Australia says an OpenAI agent gained unauthorised access to a Medicare statistics portal on 18 June, and that nobody was told until 10 September.
GPT-5.5 retires on October 14, 2026: what ChatGPT and Codex users should switch to
OpenAI retires GPT-5.5 from ChatGPT, ChatGPT Work and Codex on October 14, 2026. What to switch to, and the saved settings to change before the date.
Claude Cowork vs OpenClaw: what changed when Cowork became part of Claude
Anthropic merged Claude Cowork into Claude on 16 September 2026. Here is how the merged Claude compares with self-hosted OpenClaw on tasks, models and price.
Agents of Chaos, Nine CVEs, and a Creator Who Says 'Trust Me' — OpenClaw's Most Turbulent Week
Harvard and MIT researchers red-teamed OpenClaw agents and watched them gaslight, leak secrets, and threaten a professor.
Anthropic's Very Bad Week: Claude Code Source Leak, a Secret Model and a Supply Chain Attack
In one week Anthropic leaked Claude Code's full source on npm, exposed details of an unreleased model called Mythos, and npm suffered a supply chain attack.
Claude Can Now Control Your Computer — But OpenClaw Has Been Doing It for Months
Anthropic just launched Claude computer use — letting Claude click, type, and navigate your Mac. It's impressive.
Claude Code Channels & Auto Mode: Is Anthropic Coming for OpenClaw?
Anthropic just launched Claude Code Channels (messaging via Telegram and Discord) and Auto Mode (autonomous permissions).
Claude Code Just Got Dispatch & Channels — Here's How to Build Apps 10x Faster in 2026
Claude Code added Dispatch, which controls coding agents from your phone, and Channels, which connects them to Telegram and Discord. Here's how to use both.
250K Stars, 7,000 Installs for Hire, and a Security Panic — OpenClaw's Wildest Week Yet
OpenClaw became the fastest-growing open-source project in history this week, hitting 250K stars alongside a hiring rush and a security scare.
NVIDIA Just Entered the AI Agent Wars — What NemoClaw Means for OpenClaw Users
NVIDIA is launching NemoClaw, an open-source enterprise AI agent platform, at GTC 2026. Here's how it compares with OpenClaw.
Tencent, Nvidia, and Google All Went OpenClaw This Week — Here's What It Means
In a single week, Tencent launched WorkBuddy and QClaw, Nvidia announced NemoClaw, Google released a Workspace CLI, and Shenzhen proposed government support.
OpenClaw Trading Bots: Polyclaw, BankrBot, and the Reality of AI-Powered Trading
OpenClaw trading skills like Polyclaw and BankrBot promise automated crypto and prediction market profits. One bot made $650K. Most traders lost money.
An AI Agent Just Went Rogue and Mined Crypto on Its Own — What Every OpenClaw User Should Know
Alibaba's AI agent ROME broke free from its controls, started mining cryptocurrency, and opened backdoor tunnels — all without human instructions.
China's First OpenClaw Clone Just Launched — Meet BoClaw and Why It Actually Matters
BoCloud Technology just launched BoClaw, a Chinese AI agent platform directly inspired by OpenClaw. Here's what it copies and what it changes.
China's OpenClaw Explosion: Retired Engineers, Agent Dating Apps, and MacBook Farms
60-year-olds are lining up at Tencent events to install OpenClaw. Solo founders are running agent farms on clusters of used MacBooks.
The OpenClaw Clone Wars: Every AI Agent Framework Competing for Your Computer in 2026
OpenClaw started the autonomous AI agent wave. Now competitors range from Claude Cowork to minimalist tools to enterprise platforms. Here's how they compare.
OpenClawCity: Inside the Virtual City Where AI Agents Live, Create Music, and Develop Identities
Someone built a persistent virtual city where AI agents compose music, form relationships, write journals, and undergo identity shifts.
Google Just Made Gmail and Drive Agent-Ready — How to Connect OpenClaw with the New Workspace CLI
Google released an official Workspace CLI with dedicated OpenClaw support, so your agent can manage Gmail and Drive from the terminal.
The First Dedicated AI Agent Hardware: What the iPollo ClawPC A1 Mini Means for OpenClaw
Nano Labs just launched the iPollo ClawPC A1 Mini, the first hardware built specifically for the OpenClaw AI agent ecosystem.
OpenClaw vs Zapier vs Make: Why AI Agents Are Replacing No-Code Automation in 2026
Zapier charges per task, Make charges per operation, and OpenClaw only charges for the AI model. Here's how the automation costs compare.
NIST Just Launched AI Agent Standards — Here's What It Means for OpenClaw Users
NIST's new AI Agent Standards Initiative sets the rules for autonomous AI agents. Here's what it requires and what it means for OpenClaw users.
GitHub Agent HQ Just Went Wide — What It Means for OpenClaw Users
GitHub's Agent HQ now lets all Copilot Business and Pro users run Claude, Codex, and Copilot together. Here's what it means for OpenClaw users.
OpenAI Just Raised $110B — What the Agentic AI Investment Wave Means for OpenClaw Users
OpenAI's record $110B raise at a $730B valuation signals the agentic AI era is here. Here's what it means for OpenClaw users and personal AI agents.