openclaw-dream-setup

Configure nightly dream-memory distillation with cron scheduling and token budgets.

Updated Mar 22, 2026
One-click install
npx skills add https://github.com/diazMelgarejo/orama-system --skill openclaw-dream-setup-diazmelgarejo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openclaw-dream-setup
Source: https://github.com/diazMelgarejo/orama-system/tree/main/bin/orama-system/skills/openclaw-skills/skills/openclaw-dream-setup
Command: npx skills add https://github.com/diazMelgarejo/orama-system --skill openclaw-dream-setup-diazmelgarejo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Agents accumulate memory over time, and without a scheduled distillation routine, memory retrieval consumes active context and degrades task performance. This Skill installs a consistent nightly memory distillation pipeline with enforced token budgets so long-term memory stays curated without manual upkeep. ## Core Features & Use Cases - Memory Structure Setup: Creates DREAM-ROUTINE.md, MEMORY.md, and a memory/archives directory for a given agent. - Cron Scheduling: Registers a nightly dream job in openclaw.json with a configurable run time and a default job ID of <agent_id>-dream-nightly. - Token Budget Enforcement: Hard-caps daily distillation at 2500 tokens and rolling 3-day digests at 7500 tokens. - Startup Wiring: Updates AGENTS.md and QMD index references so memory is preloaded at session start. - Use Case: After migrating an agent to a new environment, run this Skill to rebuild its dream routine, restore memory hygiene, and standardize the process across multiple agents. ## Quick Start Set up the nightly dream-memory routine for agent 'research-bot' with a run time of 03:00 local time.

Frequently Asked Questions about openclaw-dream-setup

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

FAQPage Schema
How do I set up nightly memory distillation for an OpenClaw agent?

Provide the agent_id and a cron-compatible run_time, and the Skill creates DREAM-ROUTINE.md, MEMORY.md, and a memory/archives directory, then registers a nightly cron job in openclaw.json. The job ID defaults to <agent_id>-dream-nightly.

How do I schedule a cron job in openclaw.json?

The Skill uses jq to append a job entry with id, agentId, a cron schedule value, a prompt to run DREAM-ROUTINE.md, and isolated execution enabled. Existing jobs with the same ID are replaced rather than duplicated.

What token budgets does the dream routine enforce?

Daily distillation is hard-capped at 2500 tokens and the rolling 3-day digest at 7500 tokens. These values are fixed and must not be changed, since exceeding them causes memory retrieval to consume active task context.

Why is my agent using stale memory after setup?

Stale memory usage happens when the AGENTS.md startup sequence is missing. The Skill appends steps to read MEMORY.md, check the latest archive in memory/archives, and respect DREAM-ROUTINE.md token caps at each session start.

What happens if the memory/archives directory is missing?

A missing memory/archives directory blocks the rolling digest workflow. The Skill creates it during setup with mkdir -p, and validates that the agent directory exists before making any changes.