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".
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/autosolutionsai-didac/agent-memory-setup-v2What This Skill Does
The agent-memory-setup-v2 skill is a specialized tool designed to initialize a robust, multi-tiered memory architecture for OpenClaw agents. It structures agent information into three logical layers: HOT (immediate session state), WARM (stable preferences and active references), and COLD (long-term historical milestones). By deploying this structure, you enable the agent to manage its own knowledge base more effectively, preventing information overload while maintaining core context.
Beyond directory creation, this skill configures the integration with Google Gemini Embeddings 2. This setup allows the agent to perform semantic memory searches, enabling it to retrieve relevant information based on conceptual meaning rather than simple keyword matching. The initialization process is performed via a local bash script, ensuring no network calls or environment variable exposures occur during the configuration phase, making it a secure onboarding step for sensitive environments.
Installation
To install this skill, run the following command in your terminal: clawhub install openclaw/skills/skills/autosolutionsai-didac/agent-memory-setup-v2. Once installed, navigate to your agent workspace and execute the bash setup script: bash scripts/setup_memory_v2.sh /path/to/agent/workspace. After the file system is ready, update your openclaw.json configuration file to include the Gemini provider in your memorySearch settings. Ensure you have your Google Gemini API key ready and set it as an environment variable (GEMINI_API_KEY). Finally, finalize the installation by restarting your agent gateway using openclaw gateway restart.
Use Cases
This skill is ideal for developers building autonomous agents that require persistent context across long sessions. It is perfect for agents managing research projects, coding assistants that need to remember architecture decisions, or personal assistants tracking complex user preferences. If you find your agent is losing context or "forgetting" instructions from earlier in the day, implementing this 3-tier memory system is the recommended architectural remedy.
Example Prompts
- "OpenClaw, please set up memory for my new research agent so it can start tracking long-term milestones."
- "I need to enable semantic search memory for this agent using Gemini Embeddings 2, can you guide me through the setup?"
- "My agent is losing its history; can you run the agent memory setup process to initialize the HOT, WARM, and COLD storage layers?"
Tips & Limitations
To maximize the effectiveness of this system, try to prune your memory files periodically. While the agent handles retrieval, keeping the COLD storage organized ensures the Gemini embeddings remain high-quality and relevant. Note that this skill only performs local file operations; the actual vectorization occurs via the Gemini API when the agent's memory_search tool is invoked, which requires an active internet connection at runtime. Ensure your Gemini API key is kept secure and that you have sufficient quota for your embedding requests.
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-v2": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, external-api
Related Skills
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".
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.