Reading this is strange to me because it's exactly what I've been working towards for the last 14 years or so... But TBH, it came together piece by piece. I've built a full implementation in Node.js with a set of declarative frontend components. https://github.com/Saasufy/saasufy-components?tab=readme-ov-file#saasufy-components And https://saasufy.com/ It's surprising how much functionality you can assemble with... - Source: Hacker News / 14 days ago

I'm working on the backend your AI doesn't have to build https://saasufy.com/ For vibe coders. With a focus on: - Security - Analytics - Realtime capabilities. - Source: Hacker News / 16 days ago

This is a good article. I've been working on such infrastructure to facilitate safe vibe coding with a focus on simple access control and analytics. https://saasufy.com/ I think this is spot on but the new abstractions are yet to be popularized but I'm seeing some clear patterns arise. This is something I spend a lot of time thinking about because the new abstractions must fit within existing paradigms to provide... - Source: Hacker News / 27 days ago

This is neat. I've been dreaming of something like this to host frontends connected to my backend platform https://saasufy.com - Because it's built with WebSockets, it doesn't have CORS limitations so I can literally make Claude Code create an index.html file on my computer's file system, then open it directly from the file system by double-clicking it (served via file:// protocol) then, when I'm happy, I can grab... - Source: Hacker News / about 2 months ago

When building agent integration for my serverless backend https://saasufy.com/, I decided to use skill markdown files curl commands inside instead of building out MCP tools. The curl command is just so popular, models are really good at using it. Also I like that curl is for bash and my platform requires JSON payloads; it makes the separation clear to the agent. I find it to be very reliable. - Source: Hacker News / about 2 months ago

Oh this is awesome, will take a look. I’ve had rough experiences with Kubeflow in the past, recently I’ve been using Coder workspaces https://coder.com/ and it’s pretty good but less ML/AI integrated (but, stitched together with Ray autoscaling nodes it can get really nice). - Source: Hacker News / about 1 month ago

I'm using https://coder.com for all my development containers. I've got mine hooked up to a k8s cluster, but anything that you can provision with Terraform can be used (e.g. Docker containers). - Source: Hacker News / 3 months ago

Coder | https://coder.com/ | Multiple roles | Multiple locations | Full-time Coder is an AI software development company leading the future of autonomous coding. We empower teams to build software faster, more securely, and at scale through the collaboration of AI coding agents and human developers. Our mission is to make agentic AI a safe, trusted, and integral part of every software development lifecycle.... - Source: Hacker News / 3 months ago

Ollama is fantastic for ollama pull model && ollama run model. It's genuinely the best way to get started with local models. But when you're running them as infrastructure — serving through an OpenAI-compatible API to Coder Agents, IDE extensions, and automation — the abstraction layer starts to chafe. - Source: dev.to / 4 months ago

Run agents, lots of them, using this open source project - link [tool] - ( Added: 2026-04-11 07:42:11 ). - Source: dev.to / 4 months ago