Openclaw Auto Dream

Cognitive memory architecture for OpenClaw agents — periodic dream cycles that consolidate daily logs into structured long-term memory with importance scorin...

Security Scan

The skill's requests and instructions are coherent with a local 'memory consolidation' purpose — it reads and updates workspace memory files, creates scheduled dream runs, and generates reports/dashboards; no unrelated credentials, downloads, or external endpoints are required by the skill itself.

Purpose & Capability

Name and description claim a memory consolidation system and the instructions only require reading and writing files under the agent workspace (MEMORY.md, memory/*.md, memory/index.json, etc.). There are no requested environment variables, binaries, or external credentials that don't match the stated purpose.

Instruction Scope

SKILL.md instructs the agent to read USER.md and all unconsolidated daily logs, perform semantic deduplication, append/update MEMORY.md and related files, mark processed logs, generate dream reports, and optionally regenerate a dashboard.html. This is consistent with the purpose, but it implies the agent will read potentially sensitive personal data in the workspace and produce personalized reflections (the First Dream step explicitly asks for a natural-language personalized summary). The skill also describes export/import of complete memory bundles (memory/export-*.json), which can create portable files containing all consolidated content — valid for migration but sensitive if shared.

Install Mechanism

Instruction-only skill with no install spec, no downloads, and no code files executed. Lowest install risk — nothing is written to disk by an installer. The skill does instruct creating a cron job (a scheduler entry) but that is a runtime configuration step, not an installer pulling external code.

Credentials

The skill requests no environment variables, no credentials, and no config paths beyond workspace files that are logically part of a local memory system (MEMORY.md, memory/index.json, daily logs). The export/import features will write JSON bundles to workspace paths — expected for migration features but a privacy-sensitive capability. No hidden or unrelated secret access is requested.

Persistence & Privilege

always:false (normal). The skill instructs creating a scheduled 'cron' agentTurn that will run periodically; that gives the agent recurring write/read access to workspace files. This is coherent for scheduled consolidation, but it increases persistence and autonomy — you should verify and control the schedule and session target before enabling automatic runs. The skill explicitly says 'Do not auto-install plugins or modify config,' and it recommends (but does not auto-install) an LCM plugin.

Assessment

This skill is coherent with its stated purpose, but it has broad access to your workspace files (daily logs, MEMORY.md, index.json) and will create persistent scheduled runs if you follow its cron instructions. Before installing: 1) Backup your workspace (MEMORY.md, memory/) so you can inspect changes; 2) Run the 'First Dream' manually in a test or isolated session rather than letting it run immediately; 3) Delay or review any cron/scheduler creation until you verify behavior and outputs; 4) Be aware that export/import produces full JSON bundles (portable memory dumps) — do not share those files with untrusted parties; 5) If you are concerned about privacy, restrict the agent's file permissions or run in a sandboxed workspace. If you want additional assurance, ask the skill author for a signed provenance or for a minimal dry-run mode that reports planned changes without writing files.

OpenClaw Auto-Dream — Memory Consolidation System

Agent periodically "dreams" — scans daily logs, extracts key knowledge, consolidates into long-term memory, and sends a summary report to the user.

Core Files

File	Purpose	Mutability
MEMORY.md	Structured long-term knowledge	Append, update
memory/procedures.md	Workflow preferences, tool usage	Append, update
memory/episodes/*.md	Project narratives	Append only
memory/index.json	Metadata index (v3.0 schema)	Rebuilt each dream
memory/dream-log.md	Dream report log	Append only
memory/archive.md	Summarized older entries	Append only

Optional: LCM plugin (Working Memory layer). If not installed, prompt the user:

"Recommended: install the LCM plugin for working memory: openclaw plugins install @martian-engineering/lossless-claw"

Do not auto-install plugins or modify config.

Setup

0. First Dream (Run Immediately After Install)

After setup is complete, DO NOT wait for the cron schedule. Immediately run the First Dream:

1. Read references/first-dream-prompt.md
2. Execute every step in the current session (not isolated — user should see it happen)
3. This performs a scan of existing daily logs, consolidates them, and sends a before/after comparison report
4. The report shows the user exactly what Auto-Dream found and organized — this is the Aha moment

If the user has existing daily logs, they'll see their scattered knowledge consolidated instantly. If the instance is brand new, they'll see the memory architecture initialized and ready.

1. Initialize Files

mkdir -p memory/episodes

Ensure the following files exist (create from references/memory-template.md templates if missing):

• memory/index.json
• memory/procedures.md
• memory/dream-log.md
• memory/archive.md

2. Create Cron Job

name: "auto-memory-dream"
schedule: { kind: "cron", expr: "0 4 * * *", tz: "<user timezone>" }
payload: {
  kind: "agentTurn",
  message: "Run auto memory consolidation.\n\nRead skills/skills/openclaw-auto-dream/references/dream-prompt-lite.md and follow every step strictly.\n\nWorking directory: /home/ubuntu/.openclaw/workspace",
  timeoutSeconds: 600
}
sessionTarget: "isolated"
delivery: { mode: "announce" }

3. Verify

• Cron job created and enabled
• MEMORY.md exists with section headers
• memory/index.json exists
• memory/procedures.md exists
• memory/dream-log.md exists

Dream Cycle Flow

Each dream runs in an isolated session (see references/dream-prompt-lite.md):

Step 0: Smart Skip + Recall

Check if any unconsolidated daily logs exist in the last 7 days. All processed → still send a useful message: surface an old memory ("N days ago, you decided...") and show streak count. Never send a blank "nothing to do" message.

Step 1: Collect

Read unconsolidated daily logs. Extract decisions, facts, progress, lessons, and todos.

Step 2: Consolidate

Compare with MEMORY.md → append new content, update existing, skip duplicates. Write workflow preferences to procedures.md. Mark processed daily logs with <!-- consolidated -->.

Step 2.8: Stale Thread Detection

Scan Open Threads for items stale >14 days. Include top 3 in notification with context.

Step 3: Generate Report + Auto-Refresh Dashboard

Append to dream-log.md with change list + insights + suggestions. If dashboard.html exists, regenerate with latest data.

Step 4: Notify with Growth Metrics

Send a consolidation report showing:

• Before → after comparison (entries, decisions, lessons)
• Cumulative growth ("142 → 145 entries, +2.1%")
• Dream streak count ("Dream #14")
• Milestones when hit (first dream, 7-day streak, 100 entries, etc.)
• Top 3 stale reminders (if any)
• Weekly summary on Sundays (week-over-week growth, biggest memories)

Notification Principles

1. Every notification must deliver value — never send empty "nothing happened" messages
2. Show growth, not just changes — cumulative stats make the user feel the system is evolving
3. Surface forgotten context — stale thread reminders and old memory recalls create surprise and utility
4. Celebrate milestones — streak counts and entry milestones build habit and attachment

Manual Triggers

Command	Action
"Consolidate memory" / "Dream now"	Run full dream cycle in current session
"Memory dashboard"	Generate memory/dashboard.html
"Export memory"	Export memory/export-YYYY-MM-DD.json

Language Rules

All output uses the user's preferred language as recorded in USER.md.

Safety Rules

1. Never delete daily logs — only mark with <!-- consolidated -->
2. Never remove ⚠️ PERMANENT items — user-protected markers
3. Safe changes — if MEMORY.md changes >30%, save .bak copy first
4. Index safety — save index.json.bak before each dream
5. Privacy — follow user's existing MEMORY.md conventions for what to include

Reference Files

• references/first-dream-prompt.md — First Dream: post-install full scan with before/after report
• references/dream-prompt-lite.md — Compact prompt for daily cron use (default)
• references/dream-prompt.md — Full prompt (for manual deep consolidation)
• references/scoring.md — Importance scoring, forgetting curve, health score algorithms
• references/memory-template.md — File templates (MEMORY.md, procedures, index.json, etc.)
• references/dashboard-template.html — HTML dashboard template
• references/migration-cross-instance.md — Cross-instance migration protocol
• references/migration-v1-to-v2.md — v1→v2 upgrade guide
• references/migration-v2-to-v3.md — v2→v3 upgrade guide