agent-o-rama

Official

Train agents to learn interaction patterns.

Authorplurigrid
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Agent-o-rama trains learning agents on interaction sequences to uncover behavioral patterns, producing models compatible with cognitive-surrogate systems. It supports both traditional temporal learning and a derivational, deterministic generation path for faster pattern discovery.

Core Features & Use Cases

  • train-interaction-predictor: Build models to predict next interactions from history.
  • extract-temporal-patterns: Discover time-based behavior patterns.
  • extract-topic-patterns: Analyze topic dynamics and transitions.
  • skill-discovery: Identify latent skills in interactions.
  • derive-patterns-via-unworld: Deterministic pattern derivation for fast exploration.

Quick Start

just agent-train interactions.duckdb --epochs 100

Dependency Matrix

Required Modules

duckdbpandasnumpy

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: agent-o-rama
Download link: https://github.com/plurigrid/asi/archive/main.zip#agent-o-rama

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository