AI Dev Agent
AI-powered local development agent that converts requirements from Jira, PDFs, DOCX, and code context into validated GitHub pull requests.
Features
- Jira → PR automation
- PDF/DOCX requirement ingestion
- Framework-aware generation
- FastAPI
- Django
- aiohttp
- plain Python
- Context-aware code generation
- Validation before PR creation
- Local-first architecture
- GitHub PR automation
Install
pip install smartpr-ai
Usage
quick-pr --help
Example:
quick-pr --issue PROJ-123 --repo /path/to/repo --dry-run
Development
python -m venv .venv
source .venv/bin/activate
python -m pip install --upgrade pip
python -m pip install -e ".[dev,rag]"
pytest
ruff check .
Build locally
python -m build
twine check dist/*
Publish
This repository is configured for GitHub Actions + PyPI Trusted Publishing.
Create a release tag:
git tag v0.1.0
git push origin v0.1.0
Architecture
Requirements → Context Retrieval → AI Planning → Code Generation → Validation → GitHub PR
License
Apache License 2.0
1 maintainer
Metadata
1 maintainer
Release files for smartpr-ai 0.2.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| smartpr_ai-0.2.1.tar.gz | 11.1 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| smartpr_ai-0.2.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 25.9 kB
Release files / smartpr_ai-0.2.1.tar.gz
| Download URL | smartpr_ai-0.2.1.tar.gz |
|---|---|
| Size | 11.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d49b7f3705f10fd57fd32b5517c2bc3695dbb51fd382dfcbf09a9b0437454876
|
|
BLAKE2b-256 checksum How to use checksums |
faae84c37012b8c58783aa30ffa592888ab375fc448a445466717b84447854aa
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on May 6, 2026.
Transparency logRelease files / smartpr_ai-0.2.1-py3-none-any.whl
| Download URL | smartpr_ai-0.2.1-py3-none-any.whl |
|---|---|
| Size | 14.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
c0eb340f55d8cb6a14ecf4116767ca3de91e55c172334b93f67f553717ca7dd7
|
|
BLAKE2b-256 checksum How to use checksums |
afbeefcc3d88389c41395870b1163b7776a219313dad82ce82654b621f98c30a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on May 6, 2026.
Transparency log
