19 articles connected to this topic.
Local embeddings let your AI agent run semantic memory search without sending a token to a cloud API. Here's why they matter, how 's core OpenAI-compatible embedding provider works, and how to wire one up.
How to run a self-hosted Discord voice agent on v2026.5.7: permission audit via channels capabilities, the new 2.5s capture silence grace default, and STT tuning that stops the bot interrupting people.
OpenClaw v2026.5.3 added a bundled file-transfer plugin so agents can fetch and write binary files across paired nodes. Here's how file_fetch, dir_list, dir_fetch and file_write work, plus the default-deny path policy that keeps it safe.
How /steer and active-run steering work in v2026.5.3+: send guidance to a running session without queuing a new turn, with worked examples and the safer queue defaults from v2026.4.29.
Heartbeats let an OpenClaw agent check email, calendar, and notifications on its own. Here's how heartbeats work, how they differ from cron, and how to set up a HEARTBEAT.md checklist that doesn't burn tokens.
A practical guide to configuring safety boundaries for autonomous agents, based on real incidents from Meta researchers, red team studies, and early adopter lessons.
Complete guide to running OpenClaw on Raspberry Pi 4/5. Hardware requirements, installation, optimization tips, and what works (and what doesn't) on ARM.
Run OpenClaw on Windows using WSL2. Step-by-step installation, auto-start configuration, and tips for a smooth experience on Windows 10/11.
Set up timed automations with OpenClaw cron jobs — morning briefings, inbox checks, reminders, and recurring tasks. Complete scheduling tutorial with examples.
Understand how OpenClaw's memory system works — MEMORY.md, daily notes, memory search, and context management. Configure persistent memory that makes your agent smarter over time.
Turn a Mac Mini into a 24/7 AI assistant server. Complete setup guide covering installation, auto-start, remote access, power management, and optimization tips.
Run OpenClaw in Docker on any VPS, Raspberry Pi, or home server. Includes docker-compose, environment setup, persistent storage, and auto-restart configuration.
Build a team of specialized AI agents that work together 24/7 — a strategist, builder, content creator, and more. Step-by-step multi-agent setup guide.
Step-by-step guide to connecting OpenClaw to your phone via Telegram, WhatsApp, Signal, Discord, and iMessage — so your AI agent is always in your pocket.
Build your first custom OpenClaw skill from scratch. We'll create a stock price checker with a SKILL.md, a bash script, and zero boilerplate.
Stop drowning in email. Learn how AI agents handle email differently than rules and filters, with practical workflows for triage, drafting, and follow-ups.
Practical strategies to reduce OpenAI, Anthropic, and other AI API costs using OpenClaw's built-in cost controls, model routing, and caching.
Get your personal AI assistant running locally with OpenClaw. No server setup, no cloud fees, just results. Here's exactly how to do it in under 10 minutes.
Run a fully private AI assistant with zero API costs. This guide shows you how to set up Ollama with OpenClaw for a completely local, privacy-first experience.