Skip to main content

UnvibeCode

Reverse engineer a complex codebase into business workflows, connected code, LLM-ready context, and evidence-backed business risk findings.

Requirements

Python 3.11 or newer.

Install

Windows

py -m pip install --upgrade unvibecode
py -m unvibecode --help

Review a repository:

py -m unvibecode review --repository "D:\\Projects\\customer-support-agent"

macOS / Linux

python3 -m pip install --upgrade unvibecode
python3 -m unvibecode --help

Review a repository:

python3 -m unvibecode review --repository "/path/to/repository"

Results

UnvibeCode writes customer results under ./unvibecode_results/.

A normal review produces:

  • 00_unvibecode_results.html — start here
  • Business Workflow Map
  • Connected Code Map
  • Complete Repository Context
  • Business Risk Findings

The Business Workflow Map explains application behavior across files and services. The Connected Code Map primarily shows static code relationships and provides downloadable context for deeper LLM analysis.

No customer OpenAI API key is required. Model requests used by the hosted analysis workflow are routed through the UnvibeCode hosted gateway.

Metadata

Release files for unvibecode 0.3.7

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

Source distribution (sdist)

Source distribution for unvibecode 0.3.7
File Size Uploaded Provenance
unvibecode-0.3.7.tar.gz 339.6 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for unvibecode 0.3.7
File Interpreter ABI Platform
unvibecode-0.3.7-py3-none-any.whl Python 3 none any Details

Total release size: 674.8 kB

Release files / unvibecode-0.3.7.tar.gz

Download URL unvibecode-0.3.7.tar.gz
Size 339.6 kB
Tags Source
SHA-256 checksum
How to use checksums
70470e841f763f08d591840444c413a13264a7a4359a9018b81cfd3457b73bb8
BLAKE2b-256 checksum
How to use checksums
39c377546a8717ad8d6366d47abcf65c7667a2d5377cac23b245bea4b1545ebd
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.6

Release files / unvibecode-0.3.7-py3-none-any.whl

Download URL unvibecode-0.3.7-py3-none-any.whl
Size 335.2 kB
Tags Python 3
SHA-256 checksum
How to use checksums
f3af26a9f2e5e5655dd1dfc3b743f1eebf3b4e3e15ad3ee1bb073b6ccd1a6ad5
BLAKE2b-256 checksum
How to use checksums
8462881bf25b7e132c4b26536c9759022eaf119f80740d886d3898dea6692850
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.6

Security for unvibecode 0.3.7

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.

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