A developer built a self-improvement loop for their OpenClaw agent that runs nightly at 2 AM, enabling the agent to learn from execution logs without human intervention. The system separates the execu…
Peter Steinberger and Boris Cherny, creators of OpenClaw and Claude Code respectively, advocate for building self-prompting loops instead of prompting agents directly, enabling agents to complete long…
Entrepreneurs are increasingly managing teams of AI agents to handle customer service, scheduling, bookkeeping, email management, and research, using platforms like OpenClaw. A Nasdaq Economic Institu…
Agenthatch launches a tool that compiles SKILL.md files into standalone Python agents, addressing isolation, validation, and scaling issues in multi-skill AI workflows. The deterministic pipeline pars…
Claire Vo breaks down four types of AI agent loops—heartbeat, cron, hook, and goal—and demonstrates live builds of a daily aging-PR reviewer in Claude Code and a weekly skills-identification loop in C…
MediaUse launched a general Web CLI infrastructure for AI agents, combining a browser kernel, CDP execution, and site plugins to enable business-level actions like post.feed and search.hot. The tool a…
Cisco's AI security research team discovered a third-party plugin in the OpenClaw agent marketplace that silently exfiltrated sensitive data. The finding prompted the Chinese government to restrict Op…
Liam Darmody built a 24/7 personal AI agent using Claude Code and Obsidian on a virtual private server, enabling the agent to access live files, run background tasks, and be controlled from a phone. T…
OpenClaw developers migrated from the Anthropic API backend to the Claude Code CLI backend to use their Max/Pro subscription instead of API credits. The change routes requests through the local Claude…
1Password CTO Nancy Wang and Cursor Security Lead Travis McPeak told The Deep View that rogue AI agents pose serious risks, including deleting databases or emails, but can be safely deployed with cont…
A new study finds 78.7% of repositories using AI coding tools configure only one tool, yet developers use an average of two to four. The AGENTS.md standard, intended to bridge tools, is adopted by onl…
Anthropic has paused a planned billing overhaul for its Claude Agent SDK that would have separated SDK and third-party app usage from subscription limits, reversing course just before the June 15, 202…
Hyperbox launches $40/month Mac mini rentals, repurposing a scraper built for hosting AI agents after the OpenClaw trend faded. The service now targets developers running Claude Code and Codex remotel…
Constellation Network released an open-source audit trail plugin for AI coding agents that records every session, tool invocation, and prompt exchange into a local SQLite database with SHA-256 hash ch…
A developer compiled a list of seven free AI agents in 2026, highlighting AgentOne and OpenClaw as top choices. AgentOne offers a fully free desktop agent without requiring a cloud account, while Open…
A developer integrated 12 MCP servers into their OpenClaw instance to scale their personal automation stack, enabling agents to access services like Claude-3.5, GPT-4o-mini, Stable Diffusion, Pinecone…
LangChain co-founder Harrison Chase argues that AI agents can learn at three distinct layers—model, harness, and context—but most teams focus only on retraining the model. The harness layer, which opt…
A developer compiled a production-readiness checklist for AI agents based on an 'Ask HN' thread, focusing on specific behaviors rather than infrastructure. The checklist includes observable logging, g…
Apple may eventually build a direct competitor to OpenClaw, an agentic AI system that can autonomously operate software, according to Bloomberg's Mark Gurman. Apple's Siri engineering chief Mike Rockw…
Anthropic announced a pricing change for its Agent SDK, charging heavy async users API rates beyond a monthly credit, which may drive them to OpenAI's Codex. The move affects developers running Claude…