Skip to main content

Agent for generating and applying AI-powered coding prompts in your repository via a web UI

Project description

AiChatCoder Agent

Agent for generating and applying AI-powered coding prompts in your repository via a web UI.

The AiChatCoder Agent is a command-line tool that runs locally in your repository as part of the AiChatCoder system. It generates tailored AI prompts based on your codebase, which you can copy to a chat model (e.g., ChatGPT) via the web UI at aichatcoder.com. After receiving the chat response, the agent applies the suggested changes to your files, streamlining your coding workflow.

Overview

AiChatCoder is a system designed for developers to integrate AI assistance into their coding process. The system consists of two main components:

  • AiChatCoder Agent (this pip package): A local agent that runs in your repository to generate prompts and apply changes.
  • AiChatCoder Web UI (aichatcoder.com): A web interface for controlling the agent, generating prompts, and managing chat responses.

Workflow

  1. Run the Agent Locally: Use the aichatcoder CLI to start the agent in your repository.

  2. Control via Web UI: Open the web UI at aichatcoder.com, write a prompt (or use the agent’s suggestions), and hit "Generate."

  3. Generate Prompts: The agent analyzes your codebase and generates specific AI prompts, which are displayed in the web UI for you to copy.

  4. Interact with Chat Model: Copy the generated prompt to a chat model (e.g., ChatGPT). The chat model responds with code or instructions in a specific format.

  5. Apply Changes: Copy the chat response back to the web UI. The web UI sends the response to the agent, which applies the changes to your repository files.

Installation

Install the AiChatCoder Agent using pip:

pip install aichatcoder

Usage

This package provides a CLI for running the agent in your repository. The web UI at aichatcoder.com is required to control the agent and manage the workflow.

Initialize the Agent

aichatcoder init

This sets up the agent in your current repository.

Run the Agent

aichatcoder run

This starts the agent, which will connect to the web UI and prepare to generate prompts and apply changes.

Status

This is a mockup version of the AiChatCoder Agent.

Future versions will include:

  • Full integration with the web UI at aichatcoder.com.

  • Prompt generation for AI chat models (e.g., ChatGPT).

  • Applying changes to repository files based on chat responses.

  • Custom alias support (e.g., acc init instead of aichatcoder init).

  • Cross-platform functionality.

License

The AiChatCoder Agent is licensed under the MIT License. See the LICENSE file for details.

Credits

Created by therceman

Links

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

aichatcoder-0.0.2.tar.gz (4.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

aichatcoder-0.0.2-py3-none-any.whl (4.6 kB view details)

Uploaded Python 3

File details

Details for the file aichatcoder-0.0.2.tar.gz.

File metadata

  • Download URL: aichatcoder-0.0.2.tar.gz
  • Upload date:
  • Size: 4.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.10.16

File hashes

Hashes for aichatcoder-0.0.2.tar.gz
Algorithm Hash digest
SHA256 39ac6fcde93117ac6e319eb4d016c49c2c3937919cb2624ce704750eab7baaa0
MD5 dec5ab428e8c7da331d0a881773a50ca
BLAKE2b-256 a6b5a5624b06d958ff102002f1b8d29a661f4696cabc590bb3dcdcd9363a926a

See more details on using hashes here.

File details

Details for the file aichatcoder-0.0.2-py3-none-any.whl.

File metadata

  • Download URL: aichatcoder-0.0.2-py3-none-any.whl
  • Upload date:
  • Size: 4.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.10.16

File hashes

Hashes for aichatcoder-0.0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 39bc6ef43fe07530ea588c0054a0c1470b1b1f50d09b65c6d635ce3bb71e56a4
MD5 f70330d0edceb6beeb47759c1bf1780f
BLAKE2b-256 e68540cc7ba1baa4ee70d81f928b7cf9d469650971b642d0d9ab62c0a4342f8b

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page