Programming (General)
RSSInstead of dumping raw price data into a prompt, I treated the LLM strictly as a "Qualitative Reasoner" (the Brain) and built deterministic scripts as the "Quantitative Executors" (the Hands).
The Math Layer (Zero Hallucination): Traditional Node.js/Python scripts pull marke...
Hey HN,<p>If you’re building local AI agents (or using tools like Cursor/Claude Code), giving them a place to safely execute code and manipulate files is a headache. Running untrusted LLM-generated code directly on your machine or local Docker is risky, and managing remote SSH keys for an autom...
Hi guys,<p>I made my Restailor project open source. You're welcome to use the code in case you're looking for a new job or just want to play around with an LLM integration for this purpose. You're also welcome to use my prompts.<p>It's working end-to-end and I built the infra to ...
No issues reported on https://www.githubstatus.com/<p>But I'm seeing actions fail with:<p><pre><code> Error: Response status code does not indicate success: 401 (Unauthorized)</code></pre>
We’ve been working on HIGHTITAN—a small, open-source framework designed to handle high-concurrency data streams without the usual overhead of heavy middleware.<p>The core problem we faced: standard streaming setups were too bloated for our specific low-latency requirements. With HIGHTITAN, we moved ...
I'm a CS student at PES University and over the last few months I built Pulse, a free API uptime monitor. I wanted to share what I built and genuinely ask for advice on distribution because I'm stuck.<p>I wasn't happy with how existing free monitors handle incidents. They tell you som...
Hi HN,<p>I built AutoICD, an AI-powered clinical coding platform that converts unstructured medical text into ICD-10 and SNOMED-CT codes. This is not an LLM wrapper. The platform uses a multi-layer machine learning architecture internally, combining custom-trained models with curated medical knowled...
Hi HN,<p>I built an MCP server that exposes an API for automated clinical coding.<p>Repo:
<a href="https://github.com/fcggamou/autoicd-mcp" rel="nofollow">https://github.com/fcggamou/autoicd-mcp</a><p>It allows AI assistants that support the Model Context Prot...
With Anthropic's release of Claude Code code reviews at $25/PR, I was wondering why I wouldn't just hook up Claude Code to my own repo.<p>More generally speaking, I'd guess there to be many opportunities where spinning up and down a CC instance to handle arbitrary tasks seems use...
Back in the late 90s and early 2000s, shareware was common - but now that almost anyone can vibe code software, why aren't we seeing more shareware?
I built this because Claude Code loads every rule and skill into context on every prompt. With 50+ rules and skills installed, you're burning tokens on Docker best practices while writing a commit message.<p>ai-nexus runs a hook before Claude starts — it picks 2-3 relevant rules and skills via ...
We needed something like --dangerously-skip-permissions that doesn’t nuke your untracked files, exfiltrate your keys, or install malware.<p>Claude Code's permission system is allow-or-deny per tool, but that doesn’t really scale. Deleting some files is fine sometimes. And git checkout is someti...