Aiconn NPM | npm.io

aiconn

Handle LLM API requests in one place. Designed for speed and ease of use.

⚠️ Hint: Cursor now supports 'DeepSeek-v3' and DeepSeek-r1 out of the box! So you don't need to use it via the API. This repo can be useful for future DeepSeek Models other unsupported models

Features

🎯 Simple: Minimal configuration required
deepseek-v3 and deepseek-r1 Support
🚀 Fast: Built on H3, a high-performance server framework ~~- 🔄 Flexible: Support for multiple LLM providers~~

Why

This package acts as a bridge (proxy) between DeepSeek and Cursor, allowing us to use Composer and ensuring it works as expected, like any other API model in Cursor

Prerequisites

Create an API Key at Deepseek Platform
Signup for a free account on ngrok

Usage

Start a terminal

npx aiconn

npm -g aiconn

Cursor doesn't allow localhost as a base URL, so we need to create a reverse proxy. You can use Ngrok for example:

Start another terminal

ngrok http 6000

You will see your server address in the terminal

ngrok settings cursor

Setup Cursor like the following

Note: We can't use the real names for deepseek here since Cursor will throw an error. So we "emulate" it with gpt-4 and gpt-3.5-turbo

Cursor Model Name	Deepseek Model
gpt-3.5-turbo	deepseek-v3
gpt-4	deepseek-r1

deepseek r1 cursor settings

Options

Option	Description	Default
`--hostname`	Hostname to bind to	`0.0.0.0`
`--port`	Port to run server on	`6000`

What is the problem with deepseek API in Cursor?

If you add the deepseek API and the "deepseek-reasoning" r1 model the experience is not really great:

No active .cursorrules / "Rules for AI" allowed
Only Chat support (No Composer)

License

MIT

Courses

Learn Cursor AI: Ultimate Cursor Course
Learn to build software with AI: AI Builder Hub

See my other projects:

codefetch - Turn code into Markdown for LLMs with one simple terminal command
aidex A CLI tool that provides detailed information about AI language models, helping developers choose the right model for their needs.
codetie - XCode CLI