Skip to main content

HCAI

  • A lightweight AI command-line interface powered by Hack Club AI.

  • HCAI allows you to chat with multiple AI models directly from your terminal with streaming responses, persistent conversation history, and seamless model switching.

Story...

  • Well I wanted to use Claude and Codex together on same terminal but I don't know how to do it.
  • I found out OpenCode, installed it and tried to configure but HC blocks OpenCode.
  • So I though why not instead I build a dev tool and then HCAI was built.

Update

  • I updated the full README.
  • Well before I hardcoded the models available on Hack Club's AI website (stupid me). So now this code directly pull all the meta data of all the models via Hack Club's AI API keys.
  • Made a solid interactive terminal based frontend.
  • I got inspired from OpenCode and decided to make a frontend almost similar an AI chatbot.

What it does?

  • Basically you can switch between multiple AI Models so that you can use more than 1 AI models inside your terminal with JUST ONE COMMAND
  • So for example if you want to use Claude and Codex for Backend, Claude for Frontend, Codex for Bug Solving and Gemini for simple Q/A you can absolutely do that by switching between this 3 models bu just one command.
  • Well setup is also super simple, just past your Hack Club's AI API keys to it.
  • No hassle with configuration or any other stuff, just directly it starts and by simple commands you can switch between models.

UI/UX

  • Here have a look when you want to prompt the AI. alt text
  • And on the extreme right the name of the model. alt text
  • Your prompt is then enclosed in a curved rectangle (since i wanted it to be similar to an actual chatbot). alt text
  • Look at the output, it highlights the code and also shows the code in different colors like we see on text editor like VSCode. Basically code changes the raw markdown into more interactive and more readable output. alt text
  • As you can also see in the above image that it also displays time taken to response. alt text

Commands

  • This are commands:
Command Description
/help Show available commands
/use Switch AI model
/config Show current configuration
/clear Clear current conversation
/exit Exit HCAI
  • Well also you can use "/use ", so instead of query you write the name of AI Model for example you write Claude it will list all the Claude Models that Hack Club provides with their AI API keys.

Installation

  • Basically just use "pip install hcai" on your terminal since I published this on PyPi org.
  • Then just run "hcai" on your terminal.
  • You will get to setup it by just pasting you Hack Club's AI API key.

Run it locally?

Clone the repo

Install dependencies

  • pip install -r requirements.txt

Run HCAI

  • Run it via "py -m hcai.main" or "python -m hcai.main"

Release files for hcai 1.0.3

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for hcai 1.0.3
File Size Uploaded
hcai-1.0.3.tar.gz 27.9 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for hcai 1.0.3
File Interpreter ABI Platform
hcai-1.0.3-py3-none-any.whl Python 3 none any Details

Total release size: 57.6 kB

Release files / hcai-1.0.3.tar.gz

Download URL hcai-1.0.3.tar.gz
Size 27.9 kB
Tags Source
SHA-256 checksum
How to use checksums
8decc8681942474f11ab460a99e1a89fbdfd4cd0ec1c1a0950d0793b24595889
BLAKE2b-256 checksum
How to use checksums
5f87c2857e238de3290851d7d3fd35c5ccf3c157315fd492d309a26191be7c49
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.15

Release files / hcai-1.0.3-py3-none-any.whl

Download URL hcai-1.0.3-py3-none-any.whl
Size 29.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
b219bc1da38f1d6d5c23b8d63afd3b62c2224629e4fa4fd74138d3b74bbaac45
BLAKE2b-256 checksum
How to use checksums
a151fb0835fc62be6d36092ace9f2b17160bd498fcb08aff43c8439fbeafbc35
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.15

Release history Release notifications | RSS feed

1.0.4

2 release files

This release

1.0.3 This release

2 release files

1.0.2

2 release files

1.0.1

2 release files

1.0.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page