Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

Dandy

Build Python Versions PyPI Version Downloads

A powerful open-source Python framework that simplifies the development of artificial intelligence software.

Get Started

Start by installing with pip install dandy and then checking out our quick start guide for more steps.

Documentation

Check out the Dandy Website for documentation including tutorials and more.

Command Line

The dandy command runs the coding assistant against the current project. Run it from your project root (where dandy_settings.py lives). If no dandy_settings.py exists, dandy will instead load settings from a dandy.json file found in .dandy/dandy.json in the current directory, or ~/.config/dandy/dandy.json as a last resort before creating a settings file for you.

dandy                          # start an interactive agentic loop
dandy "fix the failing tests"  # run one request, then exit
dandy -r "one more fix"        # run one request inside the latest session
dandy -s my-session "resume me"  # run one request inside a named session
dandy -n new-name              # start a fresh, pre-named conversation
dandy --sessions               # list saved sessions
dandy --init                   # create or refresh the project AGENTS.md
dandy -d old-session           # delete a saved session
dandy -h                       # show usage

Inside the interactive session every message goes to the coding agent. /new (or /n) starts a fresh conversation, /sessions (or /s) lists or resumes saved sessions, and pressing escape twice (or /quit) exits the loop. Use the one-shot form when you only want a single answer without entering the REPL.

The CLI's model is set with CLI_CONFIG in dandy_settings.py, e.g. CLI_CONFIG = {'CODING': 'DEFAULT'} points the coding agent at the DEFAULT entry in LLM_CONFIGS.

The same settings can be expressed as JSON when you don't want a Python module. Keys are case-insensitive at the top level (llm_configs === LLM_CONFIGS), so a minimal .dandy/dandy.json looks like:

{
  "llm_configs": {
    "default": {
      "host": "api.example.com",
      "api_key": "your-key",
      "model": "your-model"
    }
  },
  "cli_config": {"coding": "default"}
}

Metadata

Release files for dandy 3.0.0a5

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

Source distribution (sdist)

Source distribution for dandy 3.0.0a5
File Size Uploaded Provenance Actions
dandy-3.0.0a5.tar.gz 123.7 kB Without provenance Details for dandy-3.0.0a5.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for dandy 3.0.0a5
File Interpreter ABI Platform Actions
dandy-3.0.0a5-py3-none-any.whl Python 3 none any Details for dandy-3.0.0a5-py3-none-any.whl

Total release size: 305.6 kB

Release files / dandy-3.0.0a5.tar.gz

Download URL dandy-3.0.0a5.tar.gz
Size 123.7 kB
Tags Source
SHA-256 checksum
How to use checksums
7f019470962e740676e96671adf3473052be36d6b82cd37b6435ce05c210aa00
BLAKE2b-256 checksum
How to use checksums
2f0b6519ed477c67efb427fe61221553104c1346b734f25efecc38a1dfa72880
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.11.18

Release files / dandy-3.0.0a5-py3-none-any.whl

Download URL dandy-3.0.0a5-py3-none-any.whl
Size 182.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
3d15e09273f33c8c52339ce8b7158c281847825beb689ada9b918f941c758c99
BLAKE2b-256 checksum
How to use checksums
f60b3bc69f760a89e4442c0ec39fb759a2cdca63df282d9d9f9d06099f004a22
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.11.18

Security for dandy 3.0.0a5

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release
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