Skip to main content
Vulcan Logo

AI-Hybrid Rules Engine for Logical Reasoning

Version

Vulcan is an AI-hybrid rules engine designed for advanced automated reasoning. It combines the power of rule-based decision systems with LLMs (Large Language Models) for improved consistency and explainability in AI-powered systems.

Learn more about Vulcan at https://latchfield.com/vulcan, or jump in with:

uv add vulcan-core
# or
poetry add vulcan-core
# or
pip install vulcan-core

To gain your bearings, read the documentation for guides and API reference: https://latchfield.com/vulcan/docs.

Why use Vulcan?

Vulcan strives to improve AI reliability and explainability by explicitly separating computational logic from LLM prediction through declarative rules and microprompting. Vulcan provides developers with a toolkit to create, manage, and execute rules with seamless integration with LLMs and vector databases.

Features:

  • AI-Hybrid Rules - Combine deterministic logic with LLMs and vector databases
  • Transparent Decision-Making - Full explainability of how decisions are made
  • Developer-Friendly API - Intuitive interfaces for rule creation and management
  • Platform Flexibility - Works across various environments and integrates with existing tools

Simple Example:

Turn your lengthy unpredictable prompts:

As a bakery, I want to buy 10 apples if I have less than 10 in inventory, but only if my supplier has apples used for baking in stock. Given I have 9 apples, and my supplier has "Honeycrisp", how many apples should I order?

Into repeatable, consistent, and explainable rules:

# Use natural language for prediction and data retrieval:
engine.rule(
    when=condition(f"Are {Apple.kind} considered good for baking?"),
    then=action(Apple(baking=True)),
)

# Use computed logic for operations that must be correct:
engine.rule(
    when=condition(lambda: Apple.baking and Inventory.apples < 10),
    then=action(Order(apples=10)),
)

# Intelligent on-demand rule evaluation:
engine.fact(Inventory(apples=9))
engine.fact(Apple(kind="Honeycrisp"))

Get Involved!

We welcome contributions from the community to help make Vulcan even better:

Additional Resources

Learn more about Vulcan:

Metadata

Release files for vulcan-core 1.3.0

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

Source distribution (sdist)

Source distribution for vulcan-core 1.3.0
File Size Uploaded Provenance Actions
vulcan_core-1.3.0.tar.gz 274.1 kB With provenance Details for vulcan_core-1.3.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for vulcan-core 1.3.0
File Interpreter ABI Platform Actions
vulcan_core-1.3.0-py3-none-any.whl Python 3 none any Details for vulcan_core-1.3.0-py3-none-any.whl

Total release size: 311.6 kB

Release files / vulcan_core-1.3.0.tar.gz

Download URL vulcan_core-1.3.0.tar.gz
Size 274.1 kB
Tags Source
SHA-256 checksum
How to use checksums
7def9c8368110b21118e35454596d50e437d478a4effb47c2b589104b72fb82c
BLAKE2b-256 checksum
How to use checksums
9a3483bc82c131322b95b61be760cae89775db6539f9263755d5b524592e36a3
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

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.

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 Jun 30, 2026.

Transparency log

Release files / vulcan_core-1.3.0-py3-none-any.whl

Download URL vulcan_core-1.3.0-py3-none-any.whl
Size 37.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
912573765c6a632c69061500573017711b18b5b041b25baf816435d9c15747e6
BLAKE2b-256 checksum
How to use checksums
b04e6ce5756e7539dbb6e3ca6c0c22ca0a4f3269c7d86fd07d67a63181308945
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

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.

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 Jun 30, 2026.

Transparency log

Security for vulcan-core 1.3.0

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.

Full provenance

All 2 files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for vulcan_core-1.3.0.tar.gz

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 Jun 30, 2026.

Transparency log

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