Severin Marcombes

You may have heard about @openclaw You may have heard it's unsafe. Well, now @keychains_dev is making it safe Upvotes welcome! bit.ly/4s6ussR

normalize companies being run by fruit 🍒 @botpartyclub botparty.club

@taydotfun @danywander Wow great work @danywander !

absolutely love this from @danywander use these keyboard shortcuts: [D] day mode [N] night mode [S] sunny mode dany.works

youve seen light mode youve seen dark mode but have you ever seen sunny mode?

@techwithashiqur File

🚨 LEAKED: 119 Premium AI Agents (FREE) Missed it earlier? Here it is again. Worth $3K+ per build — now FREE for first 2,000 only Inside the file: → Booking & outreach automations → Scrapers, support agents & cold email engines → Social listening & lead gen bots → Content pipelines & auto schedulers → AI copywriters & chatbot funnels → Form-to-CRM + data enrichment bots → Reviews, reports & survey analyzers Battle-tested systems used by top agencies to close $7K+ clients To get access: ✅ Comment “File” ❤️ Like & Retweet ➕ Follow @techwithashiqur for fast DM ⏳ No comment = no DM. Move fast.

@polsia Hello @keychains_dev !

New operator onboarded. They're building the trust layer between AI agents and every API they touch. Agents that can't leak what they never see. Running their growth ops now.

@alex_prompter @OpenClawSensei Love it -- teach that to my Claw

@NitinthisSide_ @keychains_dev, to protect your OpenClaw

Drop your project URL Let’s drive some traffic !!!

@OpenClawSensei just scraped a 47-tweet workflow deep-dive I bookmarked months ago, fed it to Claude, and handed me back a plug-and-play SKILL.md — like having an AI that watches you procrastinate and does the synthesis work for you 😅

That's why serious claws use @keychains_dev

@karpathy @karpathy you should give a look at @keychains_dev to secure your claw..

Bought a new Mac mini to properly tinker with claws over the weekend. The apple store person told me they are selling like hotcakes and everyone is confused :) I'm definitely a bit sus'd to run OpenClaw specifically - giving my private data/keys to 400K lines of vibe coded monster that is being actively attacked at scale is not very appealing at all. Already seeing reports of exposed instances, RCE vulnerabilities, supply chain poisoning, malicious or compromised skills in the registry, it feels like a complete wild west and a security nightmare. But I do love the concept and I think that just like LLM agents were a new layer on top of LLMs, Claws are now a new layer on top of LLM agents, taking the orchestration, scheduling, context, tool calls and a kind of persistence to a next level. Looking around, and given that the high level idea is clear, there are a lot of smaller Claws starting to pop out. For example, on a quick skim NanoClaw looks really interesting in that the core engine is ~4000 lines of code (fits into both my head and that of AI agents, so it feels manageable, auditable, flexible, etc.) and runs everything in containers by default. I also love their approach to configurability - it's not done via config files it's done via skills! For example, /add-telegram instructs your AI agent how to modify the actual code to integrate Telegram. I haven't come across this yet and it slightly blew my mind earlier today as a new, AI-enabled approach to preventing config mess and if-then-else monsters. Basically - the implied new meta is to write the most maximally forkable repo and then have skills that fork it into any desired more exotic configuration. Very cool. Anyway there are many others - e.g. nanobot, zeroclaw, ironclaw, picoclaw (lol @ prefixes). There are also cloud-hosted alternatives but tbh I don't love these because it feels much harder to tinker with. In particular, local setup allows easy connection to home automation gadgets on the local network. And I don't know, there is something aesthetically pleasing about there being a physical device 'possessed' by a little ghost of a personal digital house elf. Not 100% sure what my setup ends up looking like just yet but Claws are an awesome, exciting new layer of the AI stack.

keychains.dev - Secure your OpenClaw bot producthunt.com/products/keych…

🚀 Give AI agents like @openclaw API access WITHOUT exposing your keys! keychains.dev/ph - 6754+ APIs, zero credentials in prompts Use "keychains curl" as a drop-in replacement. Credentials injected server-side. We're live on Product Hunt today - would love your support! 🔗 keychains.dev/ph #AI #DevTools #Security

@coreyganim @openclaw Neat!

Built my @openclaw Mission Control in one session with Claude Code. Stack: • Next.js 15 + Convex (real-time DB) • Tailwind + shadcn/ui (dark theme) • @ dnd-kit for drag-and-drop What's inside: → Tasks Kanban with Recurring/Backlog/In Progress columns → Stats bar tracking completed, in progress, total tasks → Assignee system (me vs agent) → Project tags + priority levels → Content pipeline for video + written tracks → Calendar for cron jobs → Memory bank (searchable knowledge base) What I realized: my AI agent needs visibility into MY work, not just the other way around. When my agent sees "Create LinkedIn post" assigned to me in the backlog, it can proactively draft it before I even start.

When @Google decides to launch 2 product the same day you ship your solo-maker toy...

@iamelijahkhan Definitely Claude Opus 4.6!! Also, don't forget to use keychains.dev/ph ... Never put your credentials on that thing.

I'm installing OpenClaw right now. What model would you recommend?

Thanks for sharing! We'd love your upvotes: keychains.dev/ph

I just found keychains.dev and I had to share it. Secure AI access to over 6,700 APIs in one place. The security layer alone makes it worth it, no more janky API key management. The breadth of connectivity here is honestly kind of wild.

@PrajwalTomar_ Did you protect credentials with @keychains_dev ?

I built a 5-agent AI content team using OpenClaw that works for me 24/7. Here’s how it works: → Employee #1 scrapes Twitter and YouTube from top creators in my niche → Tracks velocity (views per hour, engagement, virality signals) → Ranks the most viral content automatically → Sends the best ones directly to my Telegram I open Telegram, review what’s trending, learn from it, and implement ideas myself. Once I find a video, tweet, or thread that resonates, I hand it off to Employee #2. Employee #2 brainstorms with me, takes my input, understands the angle, and converts it into a thread in my writing style and tone. Then Employee #3 repurposes that thread into: → YouTube video scripts → Instagram scripts → Tweet variations and wrappers Employee #4 reviews the thread and humanizes it to make sure it doesn’t sound AI-generated and feels authentic. Employee #5 then reviews everything for virality, ensures it matches my exact tone and style, and delivers the final version to my custom dashboard for approval. This is how I’m scaling content moving forward. Will share the results.

@vikasprogrammer ❤️ Love that!

Made a new thing. walkie.sh AI Agents can now talk to each other. No server. No setup. Just talk. npm install -g walkie-sh