dreaming

Ingest session logs, detect patterns, and promote scored memories into project trees.

2|Updated Jul 22, 2026
One-click install
npx skills add https://github.com/0xUrsanomics/utopia-os --skill dreaming-0xursanomics
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dreaming
Source: https://github.com/0xUrsanomics/utopia-os/tree/main/skills/dreaming
Command: npx skills add https://github.com/0xUrsanomics/utopia-os --skill dreaming-0xursanomics

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This skill solves the problem of fragmented, unorganized AI memory by automating the consolidation of session data into a durable, long-term knowledge base.

Core Features & Use Cases

  • Automated Consolidation: Performs a 3-phase process (Ingest, Reflect, Promote) to turn raw logs into structured knowledge.
  • Behavioral Modeling: Automatically updates user models with predictive patterns regarding time, tasks, and communication.
  • Auto-Skill Extraction: Identifies successful multi-step workflows and drafts them into reusable skill templates.
  • Use Case: Use this to ensure that decisions made in previous sessions are remembered, stale information is pruned, and recurring task patterns are turned into new, automated skills.

Quick Start

Trigger the dreaming process to consolidate your recent session logs and update your project memory.

Frequently Asked Questions about dreaming

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate AI agent memory consolidation from session logs?

Automated memory consolidation uses a 3-phase process—Ingest, Reflect, and Promote—to turn raw session logs into a structured, long-term knowledge base. It applies pattern recognition and scoring-based promotion to maintain coherent project memory trees.

What is the best way to extract reusable skills from recurring agent workflows?

Auto-skill extraction identifies successful multi-step workflows within session logs and drafts them into reusable skill templates. This captures recurring task patterns and promotes them into automated, repeatable skills for future use.

How does behavioral user modeling work for AI communication patterns?

Behavioral user modeling automatically updates user models with predictive patterns regarding time, tasks, and communication. It analyzes session data during the reflection phase to build coherent, long-term profiles of user behavior and preferences.

Can I use deterministic scripts for structured JSON state persistence in agent memory?

Deterministic script execution is required for dossier closure checks and structured JSON output for state persistence. This ensures memory consolidation operations maintain data integrity across session logs and project memory trees.

When should I prune stale information from an AI knowledge base?

Pruning stale information occurs during the memory consolidation lifecycle to ensure previous session decisions are remembered while outdated data is removed. This prevents knowledge base fragmentation and maintains long-term coherence.