agent-memory-setup
Set up the full OpenClaw agent memory system with 3-tier memory (HOT/WARM/COLD), daily logs, semantic search (QMD), and lossless context management (Lossless Claw). Use when onboarding a new agent, setting up memory for a fresh OpenClaw instance, or when asked to install the memory system on a new agent. Triggers on "set up memory", "install memory system", "onboard new agent memory", "memory setup", "agent onboarding", "configure agent memory", "add memory to my agent", "how do I set up memory", "initialize memory", "memory system for OpenClaw".
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/autosolutionsai-didac/agent-memory-setupWhat This Skill Does
The agent-memory-setup skill is the foundation of a sophisticated cognitive architecture for OpenClaw agents. By implementing a 3-tier memory hierarchy (HOT, WARM, COLD), it transforms standard ephemeral sessions into persistent, learning agents. The skill installs a structured directory system that segregates active task state from long-term institutional knowledge. It integrates 'Lossless Claw' for intelligent context compaction, ensuring the agent retains critical historical data without suffering from context overflow or 'amnesia.' Furthermore, it enables QMD semantic search, allowing the agent to query its entire file system based on intent and meaning rather than brittle keyword matching.
Installation
To begin, ensure you have the OpenClaw CLI installed and initialized. Run the following command in your terminal:
clawhub install openclaw/skills/skills/autosolutionsai-didac/agent-memory-setup
Once installed, navigate to your target agent workspace and execute the setup script:
bash scripts/setup_memory.sh /path/to/agent/workspace
Follow the subsequent configuration steps by copying the AGENTS.md template into your root directory and updating your openclaw.json configuration file to include the required memorySearch, compaction, and heartbeat plugin definitions as detailed in the technical documentation. Finally, restart your gateway to initialize the system.
Use Cases
This skill is ideal for:
- Onboarding new agents that require persistent knowledge of client preferences.
- Converting short-term automation scripts into long-term autonomous assistants.
- Managing complex projects where historical decisions and project milestones must be referenced.
- Improving agent reliability in long-running tasks by ensuring stable API references and workflow gotchas are retained across sessions.
Example Prompts
- "I'm starting a new agent for my project management workflow. Please run the memory setup process for this directory."
- "It feels like the agent is forgetting our previous design discussions. Can you install the memory system and configure Lossless Claw?"
- "Please perform an agent onboarding and initialize the full 3-tier memory system with semantic search."
Tips & Limitations
- Maintenance: Periodically review the daily logs (memory/YYYY-MM-DD.md). The agent can be instructed to summarize these, but human oversight is recommended for crucial policy changes.
- Storage: While 'Lossless Claw' is efficient, ensure your storage volume has sufficient headroom if your agent generates high volumes of log data daily.
- Configuration: Always match your heartbeat frequency to your agent's task intensity; an excessively frequent heartbeat might increase token consumption unnecessarily.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-autosolutionsai-didac-agent-memory-setup": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, code-execution
Related Skills
agent-memory-setup-v2
Create a 3-tier memory directory structure (HOT/WARM/COLD) for OpenClaw agents and configure the built-in memory-core plugin to use Google Gemini Embeddings 2 (gemini-embedding-2-preview) for semantic memory search. Creates memory/ directories and stub files only — no code execution or external API calls from the setup script. After setup, the agent's memory_search tool uses Gemini's cloud embedding API to index memory files. Requires a free Google Gemini API key. Use when setting up a new agent's memory system or asked about semantic memory search. Triggers on "set up memory", "memory setup", "agent memory", "gemini memory", "semantic search memory", "onboard new agent".
gamma
Create presentations, documents, social posts, and web pages via the Gamma.app API. Use when asked to create a presentation, pitch deck, slide deck, document, social media carousel, or webpage using Gamma. Also use when asked to generate slides, export to PDF/PPTX, or create content from a Gamma template. Triggers on "create a presentation", "make a deck", "gamma", "slides", "pitch deck", "create a document in gamma".
agent-memory-setup
Set up the full OpenClaw agent memory system with 3-tier memory (HOT/WARM/COLD), daily logs, semantic search (QMD), and lossless context management (Lossless Claw). Use when onboarding a new agent, setting up memory for a fresh OpenClaw instance, or when asked to install the memory system on a new agent. Triggers on "set up memory", "install memory system", "onboard new agent memory", "memory setup", "agent onboarding", "configure agent memory", "add memory to my agent", "how do I set up memory", "initialize memory", "memory system for OpenClaw".
deep-research
Conduct deep multi-phase research using parallel subagents and iterative search. Use for deep research requests, comprehensive analysis, competitive intelligence, market research, or thorough investigation of complex topics.
Autosolutions Npd Validator
Run a full NPD validation pipeline on a product concept. Orchestrates 8 specialized subagents (Research Coordinator, 5 Independent Evaluators, Devil's Advocate, Consensus Director) to produce an evidence-based GO / CONDITIONAL GO / REVISIT / NO-GO recommendation. Use when someone asks to validate a product idea, assess market fit, or evaluate whether a product should be launched.