News for hackers. Stuff that matters.

sdspurrier

Re:We Raised $5.7M to Launch Cto.new Completely for Free on Wednesday October 15, 2025 @01:57PM (#45596234)
cto.new creates a new cto chat session from the homepage

Show HN: Engine – LLM agnostic Codex alternative

https://docs.enginelabs.ai/introduction

We built Engine with the belief that a lot of backlog type software engineering tasks could be handed off to a remote AI agent and completed async with little-to-no human involvement.Recently, a wave of new models and products has attracted a lot of attention to async coding agents so I wanted to share our approach!- To solve real engineering tasks for folks working on 'serious' projects we...

( Read More... | no comments | 2 points | on HN )
Re:Show HN: Engine – A multi-LLM alternative to Codex on Tuesday May 20, 2025 @09:19AM (#44041292)
60% of the time, it works every time
Re:Show HN: Engine – A multi-LLM alternative to Codex on Tuesday May 20, 2025 @08:51AM (#44041007)
Depends on your set of tasks but we use Engine for the bottom ~50% of issues by complexity. We have a pretty good swe-bench score from a while back but it's got much better since!

We have also focused on workflow integrations so you can assign issues from Linear, Jira, Trello etc which makes it more useful for teams.

Re:Show HN: Engine – A multi-LLM alternative to Codex on Tuesday May 20, 2025 @08:45AM (#44040960)
We often find that some models perform better on certain types of repo. For example Claude 3.5/7 is typically much better at frontends. That's why we let you switch up the model for each repo.
Re:Show HN: Engine – AI-powered IDE in the browser on Wednesday October 16, 2024 @11:01AM (#41859866)
The landing page? We are working on it! I posted a link directly to the app earlier but it got flagged from top of the front page :(
We built this framework to manage increasingly complex prompts and tool calls for LLM conversations with hot swappable models. We implement this framework for our AI engineering platform at enginelabs.ai.

It allows us to guardrail and extend LLMs for different software stacks with varying degrees of restriction in a relatively clean and manageable way.

We're interested to see if this framework is useful in other applications or for custom software development configurations.

There are lots of cool AI app builders out there, but the backend often seems to be neglected.

I thought it would be cool to focus on a conversational backend builder. There's a frontend tool to try too, but it's very alpha for now.

Stack:

  - Fastify Node.js app on Fly.io  
  - libSQL database on Turso  
  - managed OAuth  
  - Vite + React app on Fly.io
Hope you enjoy giving it a try. Reach out if you hit any limits.

I'd be happy to have a discussion here.

Hi! I helped make this. We're playing around using LLM platforms as an interface to external services. In this case, a managed Postgres database and BaaS platform.

If you don't have ChatGPT Plus you can try out similar functionality on our own web app https://app.backengine.dev/sign-up-ac0eba6d-2cc3-4873-9b76-9...

Show HN: Conversational Backend as a Service ('hacker' instant access code)

https://www.backengine.dev/

Use referral code 'hacker' for instant beta sign up linkWhat does it do?- Backend (Postgres DB, auth, API) built and deployed from a conversational interface according to your spec- 'Wired up' Next.js repo (hooks, starter components) in your Github, deployed on your Vercel account- Database updates with migrations, visualizerLimitations- No database record editor- No integrated serverless...

( Read More... | no comments | 2 points | on HN )

Show HN: Build and deploy a backend and wired-up starter frontend from a chat

https://www.backengine.dev/

use referral code 'hacker' for instant/free beta invitefeatures: - Everything below with no code - a conversational interface + a few clicks - Hosted postgres DB - REST on all tables - Zero config auth (with DB RLS) - Next.js frontend starter is created in your github, deployed on your Vercel - Frontend implements auth, react hooks for all REST endpoints and starter components for...

( Read More... | no comments | 4 points | on HN )