Shodh Local
Skill by doobidoo
Why use this skill?
Enhance your OpenClaw agent with Shodh Local, a persistent, offline-first cognitive memory and knowledge graph system for semantic recall and project management.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/doobidoo/shodh-localWhat This Skill Does
Shodh Local is a comprehensive cognitive memory architecture for OpenClaw agents, designed to provide a local-first, persistent knowledge base. Unlike ephemeral chat history, Shodh Local utilizes a 3-tier memory model—working, session, and Long-Term Memory (LTM)—to ensure that your agent remembers facts, project structures, and personal preferences over time. It functions as an offline server (amber-seaslug) that stores information in a local data directory, enabling semantic recall, GTD-style task management, and a rich knowledge graph. By utilizing Hebbian learning principles, the system strengthens associations between memories based on frequency and context, ensuring that the most relevant information is retrieved when it matters most. It effectively transforms your agent from a stateless processor into a persistent digital assistant.
Installation
To install this skill, run the following command in your terminal: clawhub install openclaw/skills/skills/doobidoo/shodh-local. After installation, ensure you have the server binary ./shodh-memory-server available. Configure your TOOLS.md file by specifying the server location (localhost:3030) and providing your API key generated via the server. For visual introspection of your knowledge graph and activity, you can navigate to tools/shodh-memory and execute the TUI dashboard via ./shodh-tui. Ensure that your data directory ./shodh-data is writable by the OpenClaw process.
Use Cases
- Persistent Context: Retain project-specific details or user preferences across different sessions to maintain continuity.
- Task & Project Management: Track complex multi-stage projects using the GTD (Getting Things Done) framework built into the memory store.
- Knowledge Management: Maintain a searchable graph of learned information, technical documentation, and observations.
- Agent Autonomy: Empower sub-agents to access the same shared memory bank, allowing for seamless handoffs and collaborative task execution.
Example Prompts
- "Remember that my preferred coding style for this project is functional, and add this to my project-backend tag."
- "Recall what I learned about the API documentation last week and summarize the main integration points."
- "Check my todos for today and identify which tasks are related to the OpenClaw project that I haven't completed yet."
Tips & Limitations
To get the most out of Shodh Local, always use descriptive tags when saving memories to facilitate easier semantic retrieval. Perform a weekly maintenance routine by restarting the server via process kill amber-seaslug to clear stale session cache. While the system is robust, remember that it is a local-first tool; ensure your ./shodh-data directory is backed up regularly to prevent data loss. If you find the agent struggling with context, trigger /api/proactive_context to force a retrieval of the most relevant background information before proceeding with a complex request.
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-doobidoo-shodh-local": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, network-access