Skip to main content

A lightweight communication layer for developers to interact with LLMs.

Project description

AI Codec

PyPI version CI License: MIT

AI Codec is a lightweight, CLI-first tool that brings a structured, reviewable, and reversible workflow to applying LLM-generated code to your projects. Instead of chaotic copy-pasting from a chatbot, you get a formal, git-like review process for AI-driven changes.


📖 Full Documentation

For a complete guide, including installation options, a step-by-step tutorial, and the full command reference, please visit the official documentation website:

https://stevie1704.github.io/aicodec/


✨ Features

  • Structured Interaction: Enforces a simple JSON schema, turning raw LLM output into a structured set of changes.
  • Safe Review Process: The aicodec apply command launches a web UI with a git-like diffing experience so you can see exactly what will change before any files are touched.
  • Developer in Control: Selectively apply, reject, or even edit the LLM's suggestions live in the diff viewer.
  • Atomic & Reversible Changes: The apply and revert commands make applying LLM suggestions a safe transaction that you can undo with a single command.
  • Flexible File Aggregation: Gather relevant project files into a single context for the LLM with powerful inclusion/exclusion rules.
  • Clipboard Integration: Pipe your LLM's response directly from your clipboard into the review process.

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

aicodec-2.8.1.tar.gz (40.1 kB view details)

Uploaded Source

Built Distribution

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

aicodec-2.8.1-py3-none-any.whl (41.2 kB view details)

Uploaded Python 3

File details

Details for the file aicodec-2.8.1.tar.gz.

File metadata

  • Download URL: aicodec-2.8.1.tar.gz
  • Upload date:
  • Size: 40.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.10.9

File hashes

Hashes for aicodec-2.8.1.tar.gz
Algorithm Hash digest
SHA256 9d731e32df8bd2a77127374155ed760e9ab7a1f1ce39bdf5b91e70c0edf27746
MD5 bc5fbd43a5f15f2a814d8dacb0bae36f
BLAKE2b-256 432aa974a88b351c903b9546d827ce5c1ab0671ddcecd7f782fe41ffb979f241

See more details on using hashes here.

File details

Details for the file aicodec-2.8.1-py3-none-any.whl.

File metadata

  • Download URL: aicodec-2.8.1-py3-none-any.whl
  • Upload date:
  • Size: 41.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.10.9

File hashes

Hashes for aicodec-2.8.1-py3-none-any.whl
Algorithm Hash digest
SHA256 473889beeb87a6c942b254fe4fffebb12665370a2a34363aecb1b49e1768d378
MD5 87066276a704fe53201d1f4a44002fc8
BLAKE2b-256 44b6e6701bc4a290fd6753e3227c465c2f4bb9478122e4c5fe1e57cc4ba6e9b3

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