feat: Adding Active Inference module to ElizaOS

[docxology]

Relates to

Implementation of Active Inference (probabilistic cognitive modeling using perception and action) in ElizaOS. This plugin provides a standalone implementation of the Active Inference framework for modeling agent behavior under uncertainty.

Risks

Low risk. This is a standalone plugin, and the code consists of conventional statistical models. The implementation:

• Uses well-tested mathematical libraries (mathjs)
• Has no direct system access or privileged operations
• Is isolated from other ElizaOS components
• Contains only pure computational functions

Background

What does this PR do?

This PR introduces a TypeScript implementation of Active Inference, a computational framework for modeling perception and action in cognitive systems. Key features include:

1. Core Active Inference Engine:

   • Belief updating through variational inference
   • Action selection via expected free energy minimization
   • Configurable model parameters and learning rates

2. Two-State World Example:

   • Demonstrates safe/dangerous state inference
   • Shows action selection between stay/move behaviors
   • Includes observation-driven belief updates

3. Visualization Tools:

   • Real-time belief evolution tracking
   • Expected free energy visualization
   • State transition analysis
   • Interactive HTML reports

4. Logging and Debugging:

   • Detailed model parameter logging
   • Step-by-step inference tracking
   • Matrix operation validation
   • Belief state interpretation

What kind of change is this?

Feature addition. This PR adds a new cognitive modeling capability to ElizaOS through a self-contained plugin.

Why are we doing this? Any context or related work?

We are doing this to provide a standalone implementation of Active Inference in ElizaOS. This is a foundational capability for the ElizaOS project, and it will allow us to model agent behavior under uncertainty.

Documentation changes needed?

Yes. The following documentation has been added:

1. README.md in the plugin directory explaining:

   • Active Inference theory and implementation
   • Usage examples and API documentation
   • Configuration options
   • Visualization guide

2. Code Documentation:

   • TypeScript interfaces and type definitions
   • Function documentation with mathematical explanations
   • Example code with comments
   • Visualization script documentation

Testing

Where should a reviewer start?

1. Review the core implementation:

   • src/inference.ts - Main Active Inference implementation
   • src/types.ts - Type definitions and interfaces
   • src/utils/inference-visualizations.ts - Visualization utilities

2. Examine the example:

   • src/examples/standalone_example.ts - Complete working example
   • Output/plot_results.py - Visualization generation
   • Generated HTML report and plots

Detailed testing steps

1. Setup and Installation:

cd packages/plugin-inference
npm install

2. Run the standalone example:

python3 src/examples/standalone_example.py

3. Verify outputs:

• Check Output/inference_log.txt for detailed execution log
• Open Output/results.html to view visualizations
• Verify belief evolution and free energy plots
• Examine state transition matrices

4. Validation criteria:

• Belief updates should be mathematically sound
• Action selection should minimize expected free energy
• Visualizations should be clear and informative
• HTML report should be well-formatted and complete

5. Test different scenarios:

• Modify observation patterns
• Adjust model parameters
• Verify behavior changes

Deploy Notes

No special deployment steps required. The plugin is self-contained and requires only:

• Node.js environment
• Python 3.x with matplotlib, numpy, and pandas
• Standard npm dependencies

The plugin can be installed as a regular npm package and imported into any TypeScript/JavaScript project.

[coderabbitai]

Important

Review skipped

Auto reviews are disabled on this repository.

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

---

🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

• Review comments: Directly reply to a review comment made by CodeRabbit. Example:
  • I pushed a fix in commit <commit_id>, please review it.
  • Generate unit testing code for this file.
  • Open a follow-up GitHub issue for this discussion.
• Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
  • @coderabbitai generate unit testing code for this file.
  • @coderabbitai modularize this function.
• PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
  • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
  • @coderabbitai read src/utils.ts and generate unit testing code.
  • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
  • @coderabbitai help me debug CodeRabbit configuration file.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

• @coderabbitai pause to pause the reviews on a PR.
• @coderabbitai resume to resume the paused reviews.
• @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
• @coderabbitai full review to do a full review from scratch and review all the files again.
• @coderabbitai summary to regenerate the summary of the PR.
• @coderabbitai generate docstrings to generate docstrings for this PR. (Beta)
• @coderabbitai resolve resolve all the CodeRabbit review comments.
• @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
• @coderabbitai help to get help.

Other keywords and placeholders

• Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
• Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
• Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

• You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
• Please see the configuration documentation for more information.
• If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

• Visit our Documentation for detailed information on how to use CodeRabbit.
• Join our Discord Community to get help, request features, and share feedback.
• Follow us on X/Twitter for updates and announcements.

[github-actions]

Hi @docxology! Welcome to the elizaOS community. Thanks for submitting your first pull request; your efforts are helping us accelerate towards AGI. We'll review it shortly. You are now an elizaOS contributor!