Show HN: Enoch – Control Plane for Autonomous AI Research

Agentic research control plane: queue state, worker preflight, wake-gated execution, evidence sync, dashboard, alerts, and AI-generated paper packaging. - alias8818/enoch-agentic-research-system
4 points by aliasocracy 172 days ago github.com 1 comments
Summary not yet generated for this article.

Original Text

I built Enoch after working with OpenClaw and trying to get an agentic coding system setup with Codex. In the past, I was trying to manually generate, code, and test this all manually. Then - I figured I'd try to start automation. Too many times have I typed "Continue" and gone back to my work. I figured I could automate that. Well - Enoch is what stemmed from that.

My first implementations were a mess with OpenClaw. I'll spare you the details. I moved to n8n. n8n was not bad but it felt like I had to strong arm it to do what I wanted. Had issues, but less.

Then this system - LangGraph / FastAPI... it has been working pretty well. The papers generated seem to have meaning. Generation of ideas have shown to have some positive substance. All ideas are grounded on a basis of pass / fail or positive / negative - based on criteria set on idea generation.

I will spare you too much reading.

Disclaimer: Yes, I used Codex to help code and Claude for some verbiage. I am not new to coding but I know there is a huge stigma in the business for this AI coding assistance bits. AI has helped to allow me dump my ideas down to a worker - and not have to take the time to sit and learn to code to get ideas out. Democratized software could have a grand effect.

Comments (1 of ) ⌛

Loading more comments... ⌛
Scroll down to load more comments
No comments available.
Type to search HN and engineering blog articles
Press Escape to close  |  ↑↓ to navigate  |  Enter to open