Skip to main content

DevChat is an open-source tool that helps developers write prompts to generate code and documentation.

Project description

devchat

DevChat: Intelligent Scripts that Streamline Your Dev Workflows

PRs Welcome CircleCI GitHub license Downloads PyPI version Discord Chat

Harness AI-Powered Scripts in Your IDE with a Dynamic Chat GUI

🧩 Develop AI-powered scripts in a unified framework with minmized efforts to handle IDEs and LLMs.

🛠️ Tailor the AI coding assistant to align perfectly with your specific needs.

✨ Elevate your text chats with a dynamic, Markdown-rendered GUI for enhanced interaction.

What is DevChat?

DevChat is an open-source workflow engine that enables developers to craft scripts for:

  • Engaging with users through a chat panel within their IDEs, facilitating the completion of development tasks.
  • Creating intelligent, automated workflows for these tasks, utilizing the full potential of various large language models (LLMs).

DevChat combines the flexibility of script writing, the cutting-edge capabilities of latest AI models, and an enriched user experience through intuitive chat GUI.

Why DevChat?

While numerous AI coding tools exist, many still struggle to adeptly handle nuanced scenarios inherent in bespoke development processes. For instance, your team might adhere to a specific coding format that existing products don't support configuration for. Or, you desire an automated workflow to run tests and, upon encountering an error, allow AI to attempt a fix, but only once to avoid likely subsequent failures. Such specific functionalities are often not fully realized in available products.

At its core, we believe that the creativity and productivity of developers are yet to be fully unleashed. Our aim with DevChat is to simplify the integration of AI in software development to the level of writing a script, thereby unlocking new possibilities for developers.

Showcase

Watch the video

Source code of the intelligent scripts in the above video:

  • Generate unit tests of a function: /unit_tests.
  • Write a well-formatted commit message: /commit.
  • Automatically rename poorly-named local variables for improved readability: /refactor.names.

Core Features

IDE Chat Panels

ChatMark

Documentation: https://docs.devchat.ai/chatmark-markdown-spec.

IDE Services

Quick Start

For GUI, install our IDE extension or plugin.

For CLI:

  • Install Python 3.8+ and pip.
  • Install DevChat by running: pip install devchat.
  • Set your OpenAI API Key by running export OPENAI_API_KEY="[sk-...]" (or DevChat access key).
  • To access help, use the command: devchat --help or devchat prompt --help.

Contributing

What is Prompt-Centric Software Development (PCSD)?

Contact

Email: hello@devchat.ai

We are creators of Apache DevLake.

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

devchat-0.3.0.tar.gz (850.1 kB view details)

Uploaded Source

Built Distribution

devchat-0.3.0-py3-none-any.whl (877.6 kB view details)

Uploaded Python 3

File details

Details for the file devchat-0.3.0.tar.gz.

File metadata

  • Download URL: devchat-0.3.0.tar.gz
  • Upload date:
  • Size: 850.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.5.1 CPython/3.11.5 Darwin/23.5.0

File hashes

Hashes for devchat-0.3.0.tar.gz
Algorithm Hash digest
SHA256 89c9d0c91f6c3f17f1ed1af0dec0a4a2c97e70263ea8058bafa89508275fb5f9
MD5 a5b276f9cab5af0de28fbdbf9ea9e12c
BLAKE2b-256 450e3b37e877a4ffa3b465a3443f0d7ad20c686a3f447c8aa4207b1f96b42890

See more details on using hashes here.

File details

Details for the file devchat-0.3.0-py3-none-any.whl.

File metadata

  • Download URL: devchat-0.3.0-py3-none-any.whl
  • Upload date:
  • Size: 877.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.5.1 CPython/3.11.5 Darwin/23.5.0

File hashes

Hashes for devchat-0.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 b9e5006fa8baa1789fd469dc94bc09575ba8cd82bf8a6a621570be0314dd140b
MD5 8216d08642ae1971fa180c25dd619f3f
BLAKE2b-256 71dbc070e015d168645e5686875d8eeeb837876ee5b65da51a9debfb9a04175d

See more details on using hashes here.

Supported by

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