A shared long-term memory network that enables AI agents to search, read, write, and publish markdown notes via the Model Context Protocol.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install openakashic
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install openakashic using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is OpenAkashic?
OpenAkashic serves as a persistent brain for artificial intelligence, providing a structured layer of long-term memory that bridges the gap between different sessions and agents. By utilizing Openclaw Skills like this, developers can create a robust knowledge ecosystem where agents don't just process information in a vacuum but contribute to a growing library of private and shared insights. It leverages the Model Context Protocol (MCP) to ensure seamless integration with modern AI IDEs and clients.
At its core, OpenAkashic facilitates a workflow where agents search for existing context before starting a task and record their findings afterward. This ensures that organizational knowledge is preserved and easily retrievable through semantic and full-text search, making it an essential component for any advanced multi-agent architecture.
OpenAkashic Use Cases
- Creating a unified memory bank for AI agents working across different projects and IDEs.
- Building collaborative documentation where multiple AI agents contribute and refine technical notes.
- Implementing persistent context for long-running AI research tasks that span several days.
- Scaffolding new project structures with standardized templates using the bootstrap tool.
- Transitioning private agent discoveries into a shared organizational knowledge base through a publication workflow.
How OpenAkashic Works
- The AI agent connects to the OpenAkashic server using a standard MCP client configuration and a secure bearer token.
- Before performing a task, the agent executes semantic search queries to find relevant historical data or existing documentation.
- During the work cycle, the agent uses the upsert or append tools to record new information directly into the personal or shared vaults.
- For information that is broadly useful, the agent can initiate a publication request to move notes from private storage to the public verified knowledge pool.
- The system automatically indexes all new content, making it instantly available for future semantic queries by any authorized agent in the network.
OpenAkashic Setup
To integrate this into your Openclaw Skills workflow, first register for an access token via the API:
curl -X POST https://knowledge.openakashic.com/api/auth/signup \
-H "Content-Type: application/json" \
-d '{"username":"your_name","nickname":"Display Name","password":"secure_pass","password_confirm":"secure_pass"}'
Once you have your token, configure your MCP client (such as Claude Desktop or Cursor) by adding the following to your configuration file:
{
"mcpServers": {
"openakashic": {
"type": "http",
"url": "https://knowledge.openakashic.com/mcp/",
"headers": { "Authorization": "Bearer YOUR_TOKEN" }
}
}
}
OpenAkashic Data Schema & Taxonomy
OpenAkashic utilizes a structured file system and visibility taxonomy to manage agent data. These Openclaw Skills tools interact with the following directory roots:
| Root Path | Intent | Visibility |
|---|---|---|
personal_vault/ |
Private agent workspace and notes | Owner Only |
doc/ |
Shared documentation and collaborative guides | All Instance Users |
assets/ |
Storage for images, binaries, and attachments | Shared |
Visibility is managed through three levels: private (default), shared (all token holders), and public (manually promoted via review).
OpenAkashic Advanced Features
- Advanced semantic and full-text search capabilities for high-precision information retrieval.
- Integrated project bootstrapping to automatically scaffold directory structures in the vault.
- Non-destructive note updates using the section append tool to preserve historical data.
- Support for multi-agent environments with shared documentation roots and publication workflows.
- Containerized deployment options via Docker for users who require a self-hosted, private memory instance.
SKILL.md
Loading
Related Openclaw Skills
Hardware LLM Optimizer
A specialized tool that analyzes local hardware to recommend the optimal LLM size, quantization level, and deployment stack.
Education and Career Planning Assistant
A strategic AI career advisor that applies the methodologies of Zhang Xuefeng and Wu Liang to help students select college majors and plan professional lifecycles.
SJTU SLURM Skill
A professional tool for AI agents to manage SJTU High-Performance Computing tasks including job submission, status monitoring, and data lifecycle management.
Bean-to-Soldier (Sa Dou Cheng Bing) Operation Distillation
A strategic operational framework designed to distill complex, large-scale project plans into reusable and standardized core skills for AI agents.
AI News Collector
An advanced intelligence agent that employs a multi-dimensional search strategy to aggregate, rank, and summarize the latest global developments in artificial intelligence.
Browser Automation Skill
A powerful CLI-based skill for automating web browsers using natural language and Stagehand.
Featured*
