Hacker Newsnew | past | comments | ask | show | jobs | submit | andes314's commentslogin

I’m building ClawJetty: a small, always-on mini PC that runs a personal OpenClaw instance with minimal setup (pair from an app, connect your chat channel, done). The point is to make “self-host your agent” feel like setting up a router, not a weekend project.

Pricing is two tiers and two purchase options:

Plus: $149/mo with a 12-month commitment (box included) or $449 upfront + $119/mo

Pro: $269/mo with a 12-month commitment (box included) or $449 upfront + $219/mo

Plans include managed updates + rollback, safe defaults (no exposed inbound ports), and address collection at checkout for fulfillment. AI usage is bundled with included allowance; overages/top-ups will come later.

Looking for feedback from people who’ve self-hosted agents (or tried): what parts of setup/ops were the biggest pain, and what would you demand from an “agent appliance” to trust it?


Linear time attention doesn’t work, by principle. Dead end pursuit. Much great research on more efficient quadratic time inference


What about n log n?


SEEKING WORK, Boston, MA (open to relocation), Remote Welcome.

https://rlafuente.com

ML Engineer with experience in high visibility DARPA and DAF projects. I charge $200/hour for time spent in an interview process.


Putting my profile on here for anyone who is looking for an ML Engineer. I have worked on AI/ML development on highly visible DARPA and DAF programs. I generally charge $200/hour for time spent interviewing.


This platform is an mcp client and mcp server creator tool. You make the mcp servers from APIs. It is a “Postman” tool in two ways


It is a platform to create MCP servers from API endpoints, and then chat with them without having to use Claude’s clunky integration process. It is simple and complete.


My platform goes beyond being an automatic wrapper of an API and lets you specify to the model, in natural language, how it should parse inputs and outputs. I find LLMs are very responsive to this type of specification, and to the best of my knowledge no one is trying this yet.

You also don’t seem to offer a simple chat-based client.


If it enters hug of death, please try Claude client to test it! Anthropic allows me only 30req/s at the moment


How much are you spending on tokens right now?


Less than you’d think


For anyone confused, you can play with mcp for free on usetexture.com


There are thousands of ready-made MCP servers hosted on https://smithery.ai


This is what the no-code API-to-MCP creator uses at usetexture.com! I was surprised to find out this is not what the Claude client uses (as of May 2025)


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: