<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>OpenClaw · Agentic Feats</title><description>What people got done with OpenClaw.</description><link>https://agenticfeats.com/</link><language>en</language><item><title>Home Assistant AI agent with persona</title><link>https://agenticfeats.com/c/home-assistant-ai-agent-with-persona-openclaw/</link><guid isPermaLink="true">https://agenticfeats.com/c/home-assistant-ai-agent-with-persona-openclaw/</guid><description>OpenClaw, running in a Proxmox LXC beside Home Assistant via ha-mcp, became an always-on agent with persistent markdown memory and a raccoon persona named Claudette. Result: Claudette controls the lights and speaks through Google Home speakers in an ElevenLabs voice, shown in a live demo. Evidence: Shown. Source: https://dan-malone.com/blog/openclaw-home-assistant</description><pubDate>Tue, 13 Oct 2026 15:29:03 GMT</pubDate><category>OpenClaw</category><category>Personal and Family</category></item><item><title>Agent-built research knowledge bases</title><link>https://agenticfeats.com/c/agent-built-research-knowledge-bases-openclaw/</link><guid isPermaLink="true">https://agenticfeats.com/c/agent-built-research-knowledge-bases-openclaw/</guid><description>OpenClaw learned to use a YouTube summariser, a paper extraction tool, and QMD, then built searchable Markdown knowledge bases for videos and research papers. Result: The author now has two dense, searchable knowledge bases, one from YouTube videos and one from research papers, which they say speeds up understanding. Evidence: Shown. Source: https://notesfromzero.substack.com/p/building-knowledge-bases-for-my-openclaw</description><pubDate>Tue, 13 Oct 2026 15:29:03 GMT</pubDate><category>OpenClaw</category><category>Research</category></item><item><title>OpenClaw personal agent setup</title><link>https://agenticfeats.com/c/openclaw-personal-agent-setup/</link><guid isPermaLink="true">https://agenticfeats.com/c/openclaw-personal-agent-setup/</guid><description>The author runs OpenClaw on an old MacBook Air, talks to it through Slack, and set up a daily morning brief and a task dashboard. Result: A working personal agent that sends an 8am brief and updates a vibe-coded Kanban dashboard in real time as it works. Evidence: Shown. Source: https://prompthub.substack.com/p/how-im-using-openclaw</description><pubDate>Tue, 13 Oct 2026 15:29:03 GMT</pubDate><category>OpenClaw</category><category>Setup and Meta</category></item><item><title>VC analyst agent and CRM build</title><link>https://agenticfeats.com/c/vc-analyst-agent-and-crm-build-openclaw/</link><guid isPermaLink="true">https://agenticfeats.com/c/vc-analyst-agent-and-crm-build-openclaw/</guid><description>OpenClaw, set up as a VC analyst agent named Pao, audited its own server security and coded a basic CRM. Result: Pao fixed firewall, root SSH and Docker proxy issues for $0.30, and a basic internal CRM was built for about $25 in one weekend. Evidence: Shown. Source: https://shriftman.substack.com/p/my-first-experience-with-openclaw</description><pubDate>Tue, 13 Oct 2026 15:29:03 GMT</pubDate><category>OpenClaw</category><category>Business</category></item><item><title>OpenClaw buys from Amazon</title><link>https://agenticfeats.com/c/openclaw-buys-from-amazon/</link><guid isPermaLink="true">https://agenticfeats.com/c/openclaw-buys-from-amazon/</guid><description>OpenClaw agent used the buy-anything skill and Rye&apos;s checkout API to find, check out, and order products for Ryan Eade. Result: Ryan completed real purchases delivered to his door, replaced his Alexa buying flow, and passed the Amazon challenge on a live podcast demo. Evidence: Shown. Source: https://rye.com/blog/openclaw-buy-anything-skill-agentic-checkout</description><pubDate>Tue, 13 Oct 2026 15:29:03 GMT</pubDate><category>OpenClaw</category><category>Personal and Family</category></item><item><title>Notion control plane for agent fleet</title><link>https://agenticfeats.com/c/notion-control-plane-for-agent-fleet-openclaw/</link><guid isPermaLink="true">https://agenticfeats.com/c/notion-control-plane-for-agent-fleet-openclaw/</guid><description>The author built AgentOps, a Notion control plane that tracks, queues, logs, and alerts on their 18 OpenClaw agents. Result: Notion now tracks 18 agents and 78 logged runs; separately, an unsubscribe agent cleared 47 vendor mailing lists in two weeks. Evidence: Shown. Source: https://dev.to/aws-heroes/i-turned-notion-into-a-control-plane-for-my-18-openclaw-ai-agents-5624</description><pubDate>Tue, 13 Oct 2026 15:29:03 GMT</pubDate><category>OpenClaw</category><category>Ops and IT</category></item><item><title>Car purchase negotiation</title><link>https://agenticfeats.com/c/car-purchase-negotiation-openclaw/</link><guid isPermaLink="true">https://agenticfeats.com/c/car-purchase-negotiation-openclaw/</guid><description>OpenClaw researched Palisade prices, contacted nearby dealers, and played their quotes against each other by email for AJ Stuyvenberg. Result: The agent negotiated a $4,200 dealer discount, bringing the car to about $56k, and the buyer never visited a showroom. Evidence: Numbers. Source: https://cloudship.co.uk/blog/ai-agent-bought-a-car</description><pubDate>Tue, 13 Oct 2026 15:29:03 GMT</pubDate><category>OpenClaw</category><category>Personal and Family</category></item><item><title>Real estate agent lead scraping</title><link>https://agenticfeats.com/c/real-estate-agent-lead-scraping-openclaw/</link><guid isPermaLink="true">https://agenticfeats.com/c/real-estate-agent-lead-scraping-openclaw/</guid><description>OpenClaw scraped Zillow, Redfin and Realtor.com for agents listing 1965 to 2000 homes in the author&apos;s service area. Result: A CSV of agent leads with brokerage, phone, email, active listings, addresses and year built landed in Google Drive, and outreach had started. Evidence: Claim. Source: https://x.com/pricefoulger/status/2033271956829806891</description><pubDate>Tue, 13 Oct 2026 15:29:03 GMT</pubDate><category>OpenClaw</category><category>Sales</category></item><item><title>Email triage and drafting agent</title><link>https://agenticfeats.com/c/email-triage-and-drafting-agent-openclaw/</link><guid isPermaLink="true">https://agenticfeats.com/c/email-triage-and-drafting-agent-openclaw/</guid><description>An agent called Donna triaged three email accounts for 30 days, flagged urgent mail on Telegram, and drafted routine replies for approval. Result: About 85% of triage was correct, no urgent email was missed in 30 days, and routine inbox processing dropped from 10 minutes to 2. Evidence: Numbers. Source: https://dev.to/jarveyspecter/i-let-an-ai-agent-manage-my-emails-for-30-days-heres-what-broke-4n12</description><pubDate>Tue, 13 Oct 2026 15:29:03 GMT</pubDate><category>OpenClaw</category><category>Business</category></item><item><title>Self-updating social media agent</title><link>https://agenticfeats.com/c/self-updating-social-media-agent-openclaw/</link><guid isPermaLink="true">https://agenticfeats.com/c/self-updating-social-media-agent-openclaw/</guid><description>OpenClaw ran on a schedule across 18 cron jobs, analyzed two weeks of engagement data on X and Bluesky, and rewrote its own strategy file. Result: The agent told the author to stop posting on X and focus on Bluesky. The author followed the advice without having asked for it. Evidence: Claim. Source: https://buildtolaunch.substack.com/p/openclaw-autonomous-agent-live-demo</description><pubDate>Tue, 13 Oct 2026 15:29:03 GMT</pubDate><category>OpenClaw</category><category>Marketing and Content</category></item><item><title>Personal memory from data exports</title><link>https://agenticfeats.com/c/personal-memory-from-data-exports-openclaw/</link><guid isPermaLink="true">https://agenticfeats.com/c/personal-memory-from-data-exports-openclaw/</guid><description>OpenClaw, fed ChatGPT, Google and Instagram history via context-use, books restaurants and sends daily recommendations. Result: The agent found and booked a restaurant the author visited, and recommended a book that the author read and liked before a trip to Kerala. Evidence: Claim. Source: https://news.ycombinator.com/item?id=47476742</description><pubDate>Tue, 13 Oct 2026 15:29:03 GMT</pubDate><category>OpenClaw</category><category>Personal and Family</category></item><item><title>Complex personal tax return</title><link>https://agenticfeats.com/c/complex-personal-tax-return-openclaw/</link><guid isPermaLink="true">https://agenticfeats.com/c/complex-personal-tax-return-openclaw/</guid><description>OpenClaw read years of tax records and entity documents, built a summary, then guided the author through filing a complex return in TurboTax. Result: Filed a 137-page federal return for $129 in software and $23.90 in tokens versus an $8,000 CPA bill, in about 6 hours. Evidence: Numbers. Source: https://x.com/dvassallo/status/2039450517143974105</description><pubDate>Tue, 13 Oct 2026 15:29:03 GMT</pubDate><category>OpenClaw</category><category>Finance and Admin</category></item><item><title>CI failure triage agents</title><link>https://agenticfeats.com/c/ci-failure-triage-agents-openclaw/</link><guid isPermaLink="true">https://agenticfeats.com/c/ci-failure-triage-agents-openclaw/</guid><description>OpenClaw agents watched GitHub Actions failures, classified them, and posted analysis and issues, then grew into test generation, coverage scanning, and self-healing locators. Result: Time to diagnose a CI failure fell from 45 minutes to 6, and test flakiness dropped from 8% to 0.8%. Evidence: Numbers. Source: https://suneetmalhotra.com/blog/openclaw-production-ai-agent-runtime-2026</description><pubDate>Tue, 13 Oct 2026 15:29:03 GMT</pubDate><category>OpenClaw</category><category>Coding</category></item><item><title>Nine OpenClaw agents</title><link>https://agenticfeats.com/c/nine-openclaw-agents/</link><guid isPermaLink="true">https://agenticfeats.com/c/nine-openclaw-agents/</guid><description>Claire Vo built nine OpenClaw agents covering sales, business operations, scheduling, family logistics, and kids&apos; education, after starting with a single executive-assistant agent. Result: One agent now does the CRM management and customer email drafting that cost about 10 paid hours a week last year. Evidence: Numbers. Source: https://aol.com/articles/startup-founder-explains-why-she-054950405.html</description><pubDate>Tue, 13 Oct 2026 15:29:03 GMT</pubDate><category>OpenClaw</category><category>Business</category></item><item><title>Freelance ops on autopilot</title><link>https://agenticfeats.com/c/freelance-ops-on-autopilot-openclaw/</link><guid isPermaLink="true">https://agenticfeats.com/c/freelance-ops-on-autopilot-openclaw/</guid><description>OpenClaw sends a morning PR and Slack briefing, drafts Friday client status emails, and queues follow-up drafts for approval on Telegram. Result: The author says weekly admin dropped from about 9 hours to a short morning review on Telegram, with setup taking 47 minutes. Evidence: Numbers. Source: https://dev.to/farooqshabbir/i-built-a-247-freelance-operations-agent-with-openclaw-it-runs-my-business-while-i-sleep-4lde</description><pubDate>Tue, 13 Oct 2026 15:29:03 GMT</pubDate><category>OpenClaw</category><category>Business</category></item><item><title>Office grocery ordering via ChatGPT</title><link>https://agenticfeats.com/c/office-grocery-ordering-via-chatgpt-openclaw/</link><guid isPermaLink="true">https://agenticfeats.com/c/office-grocery-ordering-via-chatgpt-openclaw/</guid><description>An OpenClaw assistant named Gila collects office grocery requests from Slack, then uses ChatGPT&apos;s Instacart app to build the cart and post the link back. Result: Gila ordered fresh office groceries through the ChatGPT Instacart app, using the card already on file, with a human approving first. Evidence: Shown. Source: https://nekuda.substack.com/p/we-connected-openclaw-with-instacart</description><pubDate>Tue, 13 Oct 2026 15:29:03 GMT</pubDate><category>OpenClaw</category><category>Ops and IT</category></item><item><title>Daily trending posts for content</title><link>https://agenticfeats.com/c/daily-trending-posts-for-content-openclaw/</link><guid isPermaLink="true">https://agenticfeats.com/c/daily-trending-posts-for-content-openclaw/</guid><description>OpenClaw uses the author&apos;s socialcrawl API to send a morning digest of trending posts from X, Threads and LinkedIn, used as references for writing. Result: In one week the author&apos;s Threads posts reached 100K views and gained 200 followers after using the daily digest as a writing reference. Evidence: Numbers. Source: https://news.ycombinator.com/item?id=47838224</description><pubDate>Tue, 13 Oct 2026 15:29:03 GMT</pubDate><category>OpenClaw</category><category>Marketing and Content</category></item><item><title>Marketing agents on OpenClaw</title><link>https://agenticfeats.com/c/marketing-agents-on-openclaw/</link><guid isPermaLink="true">https://agenticfeats.com/c/marketing-agents-on-openclaw/</guid><description>The author built three OpenClaw agents for marketing research, long-form content structure, and copywriting drafts, and relied on them in daily work. Result: The research agent saved the author two to three hours a week; the copywriting agent removed the blank-page first draft. Evidence: Numbers. Source: https://cgtech.com.au/microsoft-scout-always-on-agents-have-arrived-and-they-run-on-your-desktop</description><pubDate>Tue, 13 Oct 2026 15:29:03 GMT</pubDate><category>OpenClaw</category><category>Marketing and Content</category></item><item><title>World Cup reels for app signups</title><link>https://agenticfeats.com/c/world-cup-reels-for-app-signups-openclaw/</link><guid isPermaLink="true">https://agenticfeats.com/c/world-cup-reels-for-app-signups-openclaw/</guid><description>OpenClaw tracked World Cup results and had Claude post a templated Instagram trial reel after each match. Result: Ben Guez reports over one million views and 200 DMs within a few days, with replies routed to his language app. Evidence: Shown. Source: https://techcrunch.com/2026/07/02/yep-were-using-openclaw-to-date-now</description><pubDate>Tue, 13 Oct 2026 15:29:03 GMT</pubDate><category>Claude Code</category><category>OpenClaw</category><category>Marketing and Content</category></item><item><title>OpenAI build-fix agent on OpenClaw</title><link>https://agenticfeats.com/c/openai-build-fix-agent-on-openclaw/</link><guid isPermaLink="true">https://agenticfeats.com/c/openai-build-fix-agent-on-openclaw/</guid><description>An OpenAI engineer reports an internal OpenClaw agent, Androidclaw, working across Git, GitHub and logs to trace broken builds back to their causes. Result: Androidclaw traces broken builds to the relevant pull request and incident, and sometimes prepares and merges fixes itself. Evidence: Claim. Source: https://venturebeat.com/orchestration/openclaw-launches-free-enterprise-control-plane-for-persistent-ai-agents-backed-by-openai-red-hat-and-nvidia</description><pubDate>Tue, 13 Oct 2026 15:29:03 GMT</pubDate><category>OpenClaw</category><category>Coding</category></item><item><title>Movie ticket booking skill</title><link>https://agenticfeats.com/c/movie-ticket-booking-skill-openclaw/</link><guid isPermaLink="true">https://agenticfeats.com/c/movie-ticket-booking-skill-openclaw/</guid><description>The author had their Muse agent build a reusable skill that books movie tickets, handling calendar checks, seat choice, purchase, and a reminder to leave. Result: The agent built a skill that checks the calendar, buys the ticket via its wallet, adds the event, and sends a leave-time message. Evidence: Claim. Source: https://x.com/jjenglert/status/2108260489197130058</description><pubDate>Tue, 13 Oct 2026 15:29:03 GMT</pubDate><category>OpenClaw</category><category>Other</category><category>Personal and Family</category></item><item><title>Household automation add-ons for OpenClaw</title><link>https://agenticfeats.com/c/household-automation-add-ons-for-openclaw/</link><guid isPermaLink="true">https://agenticfeats.com/c/household-automation-add-ons-for-openclaw/</guid><description>The author built OpenClaw add-ons for outbox messaging, trips, flights, and Instacart carts that run their family&apos;s household on a Mac Mini. Result: In daily production use: Instacart carts auto-staged twice weekly at 100% item accuracy, plus flight alerts and scheduled iMessages without an LLM. Evidence: Shown. Source: https://github.com/kmanan/spratt-skills</description><pubDate>Tue, 13 Oct 2026 15:29:03 GMT</pubDate><category>OpenClaw</category><category>Personal and Family</category></item><item><title>Overnight builds and inbox triage</title><link>https://agenticfeats.com/c/overnight-builds-and-inbox-triage-openclaw/</link><guid isPermaLink="true">https://agenticfeats.com/c/overnight-builds-and-inbox-triage-openclaw/</guid><description>OpenClaw on a Raspberry Pi 5 triages email, builds code from a TODO list overnight, and sends daily research reports to a security consultant. Result: A VS Code extension was built overnight with 91 of 91 tests passing and a PR opened, costing about $0.35. Evidence: Numbers. Source: https://simonroses.com/2026/02/my-experience-using-openclaw-a-security-professionals-journey</description><pubDate>Tue, 13 Oct 2026 15:29:03 GMT</pubDate><category>OpenClaw</category><category>Business</category></item></channel></rss>