Skip to main content

VibeML

Machine learning for vibe coders.

Build predictions into your app without becoming an ML engineer. Ask your coding agent what you want to predict — VibeML manages the ML.

⚠️ Early placeholder release. VibeML is under active development. This version reserves the package name and sketches the CLI; the real functionality is landing milestone by milestone at github.com/vibeml-dev/vibeml.

What VibeML will do

  • "Which customers will cancel?" — learn from your historical outcomes
  • "What will this house sell for?" — predict numbers from your data
  • "Can I replace this GPT categorizer with something cheaper?" — distill repetitive LLM calls into small, fast, specialized models

Your coding agent (Claude Code, Codex) writes the code and integrates the predictions. VibeML manages the process on top: durable state for every learned Feature, a protected held-out test set so quality numbers stay honest, version history with regression review, and a local UI that explains everything in plain language.

Try it

uvx vibeml

Follow along at vibeml.dev.

License

Apache-2.0

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

vibeml-0.1.0.tar.gz (240.5 kB view details)

Uploaded Source

Built Distribution

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

vibeml-0.1.0-py3-none-any.whl (243.8 kB view details)

Uploaded Python 3

File details

Details for the file vibeml-0.1.0.tar.gz.

File metadata

  • Download URL: vibeml-0.1.0.tar.gz
  • Upload date:
  • Size: 240.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.12.3 {"installer":{"name":"uv","version":"0.12.3","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for vibeml-0.1.0.tar.gz
Algorithm Hash digest
SHA256 dd4af990a7d4d6faf38626b52029df79bacbc9e0c7eaa77e3a8ee8510ea326d9
MD5 4634d74e31d55eea9c2fa0afaac75d07
BLAKE2b-256 76f4dd167ff0aebca8fefcbe2e788ffd8ddea2f36690b46e02911c1ccf2419af

See more details on using hashes here.

File details

Details for the file vibeml-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: vibeml-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 243.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.12.3 {"installer":{"name":"uv","version":"0.12.3","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for vibeml-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 da1b7fde76367a541b9b34a4e7acf7a3335ea54b7c10de71a61d4e0235df97b5
MD5 6bc5ea722715ecb6638ceb6570343ed0
BLAKE2b-256 31bebc2fe44d0017b643e8ce4d4bc4e8a5a816ab110a5e5775569bb9bbf4ff92

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