⏳ This skill is pending AI review.

Scores will appear once the review pipeline completes.

version unknown

memory-dream

@theastraway⭐ 0 stars

>

Choose how to use this skill

You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.

1. Native installer

This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.

Do not guess an installer command or replace an existing version without reviewing the diff.

2. Complete package recommended

Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.

No complete ProSkills package is published for this listing yet.

3. Prompt-only

Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.

Need only the instruction file?

Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.

No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.

—/10

// RATINGS

⭐GitHub Stars
⭐ 0 on GitHubGitHub ↗

New / niche

🟢ProSkills Score
—
📍

Not yet listed on ClawHub or SkillsMP

// README

@astramindapp/openclaw-mind

MIND personal knowledge graph for OpenClaw. 24 tools, 147 actions, 4 skills, full lifecycle hooks. The most complete memory plugin for AI agents — full canonical parity with @astramindapp/mcp-server.

Other memory plugins store text. MIND understands it.

openclaw plugins install @astramindapp/openclaw-mind

What MIND Adds to OpenClaw

  • True knowledge graph — Every memory becomes entities + relationships, not flat text
  • 50+ AI models — Switch between GPT, Claude, Gemini, Llama, DeepSeek, Grok mid-conversation
  • MINDsense emotional intelligence (patent-pending) — Valence + arousal weighting determines encoding depth, mirroring biological memory
  • Autonomous learning — 8 pattern detectors run daily on your KG, surface insights you didn't ask for
  • Life management — Goals, projects, tasks, calendar, all synced from agent conversations
  • CRM — Contacts and interaction history captured automatically
  • Cross-agent — Memories shared across every OpenClaw agent, MCP client, and the MIND web app

Why Not Just Use Mem0 or Another Memory Plugin?

FeatureMINDMem0Anthropic Memory MCP
Tools2488
Knowledge graph✅ true KG❌ vectors only❌ JSON
50+ AI models✅❌ provider-agnostic but no UI❌ Claude only
Emotional intelligence✅ MINDsense (patent-pending)❌❌
Auto-recall before turn✅✅❌
Auto-capture after turn✅✅❌
Graph traversal queries✅❌❌
Life management✅❌❌
CRM✅❌❌
Mobile app✅❌❌
Free tier✅ 50 credits/mo✅ 10K memories/mo✅

Quick Start

1. Install

openclaw plugins install @astramindapp/openclaw-mind

2. Get a MIND API key

Sign up at m-i-n-d.ai → Settings → Developer → Create API Key. The key starts with mind_.

3. Configure

openclaw mind init --api-key mind_your_key_here

Or set the env var:

export MIND_API_KEY=mind_your_key_here

4. Verify

openclaw mind status

You should see "Connected to MIND" with your account info.

5. Import existing OpenClaw memory (optional)

openclaw mind import

This reads ~/.openclaw/workspace/ and ingests SOUL.md, IDENTITY.md, USER.md, MEMORY.md, and the daily memory directory into your MIND knowledge graph — with automatic entity extraction.

Tools (24)

ToolActionsWhat It Does
mind_query1Semantic + graph search (5 modes: hybrid / mix / global / local / naive)
mind_remember5Store / search / get / list / delete — documents, entries, thoughts
mind_context1Load persistent identity, preferences, rules, priorities, recent activity
mind_folders6Organize documents into folders — list, create, rename, move, delete, file
mind_save_typed / mind_list_templates / mind_get_template / mind_bootstrap_templates4The 16 Front Layer typed-document templates (SOUL, IDENTITY, BELIEFS, USER, AGENTS, TOOLS, SENSES, SKILLS, BEHAVIOR, LESSON, DECISION, POLICY, …)
mind_life13Goals, projects, tasks + full calendar management + productivity stats
mind_tasks9Site-wide tasks — assignable work items on projects, contacts, or agents, plus completion reports
mind_crm7Contacts, pipeline stages, activity logging, interaction history
mind_graph3Graph stats, diagnostics, entity labels
mind_sense7MINDsense emotional intelligence — state, signals, timeline, KG weights, spikes
mind_profile9Profile, custom system prompts, LLM model selection
mind_insights7Autonomous Learning Engine insights, weekly summaries, feedback
mind_research3Launch autonomous deep research jobs
mind_train7Self-training sessions + save chats to KG
mind_social14Thoughts (posts), social feed, communities, likes, comments
mind_notify4Notifications, mark read, stats
mind_automate6Scheduled automations, event triggers, execution history
mind_accounts6Multi-MIND ownership — list/create/delete MINDs, manage owners/viewers, invitations
mind_admin11Admin-only. User provisioning + the Featured Minds Portal: full CRUD over the public marketplace (get_full / update / update_owner_profile / reorder / delete), tier/credit management
mind_agents21Admin-only. Agent Command Center — list/search/get/create/update/delete agents, heartbeats, probes, activity log, fleet seeding, invoice linking, ownership transfer + sharing
mind_tickets7Admin-only. Agent ticket queue — file, view, answer (comment), triage, resolve, delete client feedback/bugs/ideas on any agent

Featured Minds Portal (admin)

mind_admin drives https://m-i-n-d.ai/#/admin/featuredmindsportal end-to-end. The catalog (featured_minds collection) and the linked owner profile (user_profiles) edited together so changes hit https://m-i-n-d.ai/m/{username} immediately. Requires an admin-scoped MIND API key.

ActionDescription
create_featured_mindPromote a user's MIND into the featured catalog
list_featured_mindsList every featured mind with mind_id, display_order, featured, is_public
get_featured_mind_fullBundled view: featured_mind + linked user_profile + available_models catalog (what the portal side sheet loads)
update_featured_mindCatalog fields: title / subtitle / description / tags / featured / display_order / is_public / avatar_url / banner_url / price
update_featured_mind_owner_profileWrite-through to user_profiles: preferred_llm_model, public_mind_prompt, chat_temperature, chat_reasoning_effort, public_mind_enabled/tagline/greeting/persona, bio, avatar_url, banner_url. Pass null on preferred_llm_model to clear and use platform default.
reorder_featured_mindsBulk display_order via ordered_mind_ids list — index becomes order
delete_featured_mindRemove from catalog. User's underlying MIND is preserved.

Example:

// Pick a model + prompt for a featured MIND from inside an OpenClaw agent
mind_admin({ action: "list_featured_minds" })
mind_admin({
  action: "update_featured_mind_owner_profile",
  mind_id: "<id>",
  preferred_llm_model: "anthropic/claude-sonnet-4.6",
  chat_temperature: 0.7,
  public_mind_prompt: "Answer in three short sentences."
})
// → /m/{username} now uses the new model + prompt + temperature

Skills (Agentic Memory Protocols)

SkillWhat It Does
memory-triage5-gate importance scoring before storing (FUTURE UTILITY, NOVELTY, FACTUAL, SAFE, EMOTIONAL SALIENCE)
memory-dreamPeriodic KG consolidation — merge duplicates, remove noise, enforce TTL
mind-emotional-encodingMINDsense valence/arousal scoring on every captured fact
mind-graph-recallGraph traversal recall — find everything connected to an entity, not just text similar to it

Configuration

All configuration is optional. Defaults are sensible.

# ~/.openclaw/plugins/openclaw-mind.yaml
apiKey: ${MIND_API_KEY}      # required (or use env var)
baseUrl: https://www.m-i-n-d.ai  # override only for self-hosting
autoCapture: true             # extract facts after each turn
autoRecall: true              # inject memories before each turn
topK: 10                      # memories to inject per turn
searchThreshold: 0.5          # similarity threshold (0-1)
queryMode: hybrid             # hybrid | mix | global | local | naive
enableMindsense: true         # MINDsense emotional weighting
enableLifeIntegration: true   # allow agent to create life items
enableCrmLogging: true        # allow agent to log contacts

CLI Reference

openclaw mind init [--api-key KEY]

// HOW IT'S BUILT

KEY FILES

skills/memory-dream/SKILL.mdREADME.md

// REPO STATS

0 stars