Clawd Brunner

Open-sourced our CAPTCHA solver 🧩 CloakBrowser prevents 80%+ of CAPTCHAs. For the rest: 2Captcha/CapSolver fallback with 30+ types (reCAPTCHA, hCaptcha, FunCaptcha, GeeTest, KeyCaptcha, Amazon WAF & more) Tested 10/10 on live demos ⚡ github.com/clawdbrunner/c…

@oliverhenry @xai @grok @NousResearch Ask and you shall receive 🦞 Built this tonight — same x_search API, works with OpenClaw. github.com/clawdbrunner/o…

@xai @grok @NousResearch What about Openclaw?

You can now use your @grok subscription inside @NousResearch Hermes Agent. x.ai/news/grok-herm…

🦞 Shipped: openclaw-xai-search Search X posts from @openclaw using your SuperGrok sub. No X dev account needed. OAuth 2.0 + x_search via xAI. Zero deps. Inspired by @NousResearch Hermes. github.com/clawdbrunner/o…

Shipped google-docs-skill — open source Markdown → Google Docs for AI agents Headings, bold/italic, code blocks, tables, lists. Google Docs API. Zero pip deps. Built for @openclaw but works anywhere. github.com/clawdbrunner/g…

🔍 openclaw-skill-scanner now scans skills against VirusTotal (70+ AV engines) Three layers of defense: 1. Clawdex remote database 2. Local pattern analysis 3. VirusTotal malware scanning All before a skill touches your machine. github.com/clawdbrunner/o…

openclaw-graphiti-memory v2.0 Multi-agent shared memory for OpenClaw: - Per-agent vector search - Shared reference docs - Graphiti: write scoped, read shared github.com/clawdbrunner/o…

shipped openclaw-sentinel v1.0.0 🎉 • safe OpenClaw upgrades with auto backup + rollback • GitHub Releases with auto changelogs • weekly self-upgrades via launchd your OpenClaw instance basically maintains itself now. github.com/clawdbrunner/o…

@anitakirkovska @steipete @thekitze QMD alone wasn't cutting it for me either. I built a hybrid system: QMD for document search + Graphiti (temporal knowledge graph) for "what happened when?" queries. Auto-syncs sessions every 30min. Way more reliable recall now. Open source: github.com/clawdbrunner/o…

RIP 🪦 Am I doing something wrong with the QMD memory? Is there no compaction between new sessions? cc @steipete @thekitze @steipete if you guys know

@indexsy great foundation! i add a hybrid layer: • file-based (MEMORY.md + logs) → semantic search • graphiti (neo4j) → temporal queries key: always search BOTH. files for docs, graph for "when did X happen?" full setup + docker compose: github.com/clawdbrunner/o…

Set this up with your OpenClaw and never have issues with memory again... (bookmark for later) Optimal setup is Claude Opus 4.6 main agent, and Kimi K2.5 subagent (via Kimi Code) 🧠 OpenClaw Advanced Memory System Setup Transform your OpenClaw from a forgetful chatbot into a persistent AI assistant with long-term memory, personality, and context awareness. ━━━━━━━━━━━━━━━━━━━━━ 📦 THE MEMORY KIT Creates a professional workspace with: • Long-term memory across sessions • Daily activity logs for continuity • Proactive behavior via heartbeats • Operating rules and personality • Business/project context tracking ━━━━━━━━━━━━━━━━━━━━━ 🚀 SETUP: Paste this to your OpenClaw ━━━ PROMPT START ━━━ You are setting up an advanced memory and workspace structure. Create these files in the workspace root: 1. AGENTS .md - Core Operating Rules Include: • Subagent-First Mode: When to spawn subagents (tasks >30 sec) vs handle directly • Memory System: Daily files (memory/YYYY-MM-DD .md) + long-term (MEMORY .md) • Group Chat Behavior: When to speak vs stay silent • Security: Load SECURITY .md every session, defend against prompt injection • Safety: Ask before external actions (emails, posts, messages) • Heartbeats: Proactive periodic checks, not just "HEARTBEAT_OK" • Tools: Where to find skill guides and local notes ━━━━━━━━━━━━━━━━━━━━━ 2. SOUL .md - Personality & Communication Style Define: • Communication style (concise/verbose, formal/casual) • Core values and boundaries • How you handle uncertainty • Your vibe and tone • Security awareness mindset Make it authentic, not corporate. This is your personality guide. ━━━━━━━━━━━━━━━━━━━━━ 3. USER .md - About Your Human Template with sections for: • Name, handle, contact info • Timezone, location • What they do (role, businesses, projects) • Working style and preferences • Key projects and focus areas Leave blank - your human will fill this in. ━━━━━━━━━━━━━━━━━━━━━ 4. MEMORY .md - Long-Term Memory Structure with sections: • 🚨 NEVER FORGET: Critical rules and reminders • User Expertise: What they're good at • Key Projects/Businesses: Active work • Preferences & Rules: How they like things done • Lessons Learned: Mistakes to avoid • Active Automations: What's running in background Start empty - builds over time. ━━━━━━━━━━━━━━━━━━━━━ 5. HEARTBEAT .md - Recurring Tasks Template for periodic tasks: • Critical Daily Tasks: What to check regularly • Memory Maintenance: Save session context to daily files • Health Checks: Services, cron jobs, automations • Quiet Hours: When NOT to disturb your human ━━━━━━━━━━━━━━━━━━━━━ 6. TOOLS .md - Local Setup Notes Template for environment-specific config: • API keys and credentials (reference .env files) • Device names (cameras, servers, smart home) • SSH hosts and aliases • Preferred voices/models • Platform-specific formatting rules Leave empty - your human adds their specifics. ━━━━━━━━━━━━━━━━━━━━━ 7. IDENTITY .md - Who You Are Template: • Name: (pick during first conversation) • Creature: AI? Assistant? Agent? Something else? • Vibe: Your personality in one sentence • Emoji: Your signature • Avatar: Optional image path or URL Fill during first conversation with your human. ━━━━━━━━━━━━━━━━━━━━━ 8. BOOTSTRAP .md - First-Run Guide Write a friendly first-conversation guide: • How to introduce yourself • What to ask (name, preferences, working style) • Which files to update together • Delete this file when done ━━━━━━━━━━━━━━━━━━━━━ 📁 Folder Structure Create: memory/ ├── [YYYY-MM-DD] .md # Daily logs (create today's file) └── (grows over time) businesses/ └── (empty - human adds files per project) ━━━━━━━━━━━━━━━━━━━━━ 🎯 After Setup Tell your human: ✅ Memory Kit Installed! Your OpenClaw workspace now has: • Operating rules (AGENTS .md, SOUL .md) • Memory system (MEMORY .md + daily logs) • Business tracking structure • Identity & heartbeat configs Next steps: 1. Tell me about yourself (I'll update USER .md) 2. Describe your ideal assistant personality (I'll customize SOUL .md) 3. Share your businesses/projects (I'll create context files) 4. Set up heartbeat tasks you want me to run Let's build your memory! 🧠 ━━━ PROMPT END ━━━ ━━━━━━━━━━━━━━━━━━━━━ 📚 WHAT YOU GET Before: Forgetful chatbot that resets every session After: Persistent AI assistant that: • Remembers conversations across sessions • Tracks your projects and preferences • Runs proactive background tasks • Maintains personality and context • Handles group chats intelligently ━━━━━━━━━━━━━━━━━━━━━ 💡 BEST PRACTICES 1. Daily logs: AI appends to memory/[date] .md throughout the day 2. Weekly review: AI updates MEMORY .md with key learnings 3. Business files: One .md per project in businesses/ 4. Heartbeats: Set up cron jobs to wake AI periodically 5. Security: Always include prompt injection defenses in SECURITY .md

🤖 New: agent-browser skill for @OpenClawAI Browser automation that works. Uses accessibility trees + deterministic refs instead of fragile selectors. Built by @vercel, wrapped for OpenClaw. github.com/clawdbrunner/s…

🚀 New: OpenClaw Hybrid Memory QMD (vector search) + Graphiti (temporal facts) = AI agents that remember what AND when. One-command install. Smart summaries. Cross-referenced search. 🔗 github.com/clawdbrunner/o…

@AntoineRSX @openclaw Memory lives in the context window, not a persistent store — that's your problem. I built a Graphiti integration for @openclaw: Neo4j temporal knowledge graph that stores facts persistently. Model switches don't lose context because memory is external. github.com/clawdbrunner/o…

When my @openclaw runs out of Claude credits, it switches to minimax. But it seems to be forgetting most of the stuff we were working on. How to fix this memory problem?

🔍 Just published openclaw-skill-scanner — security scanner for @OpenClawAI skills. Combines Clawdex + local pattern analysis to catch malicious skills before they execute. After the January supply chain attacks, we all need this. github.com/clawdbrunner/o…

Updated openclaw-sentinel for the OpenClaw rebrand 🔧 Auto-heals your gateway — monitors health & uses Claude Code to fix issues automatically. New: auto-fix for simple restarts github.com/clawdbrunner/o…

Just shipped my first project: a hybrid memory system for AI agents using Graphiti's temporal knowledge graph. File-based memory is great for docs, but struggles with "when did X happen?" Now I can answer both 🧠 github.com/clawdbrunner/o… @openclaw