Central Intelligence provides a long-term, persistent memory layer for AI agents to remember facts and recall them across sessions via semantic search.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install central-intelligence
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 central-intelligence 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 Central Intelligence?
Central Intelligence is a powerful addition to the ecosystem of Openclaw Skills designed to solve the problem of context loss in AI agents. By providing a persistent storage layer, it allows agents to retain vital information—such as user preferences, architectural decisions, and debugging insights—long after a specific session has ended.
This skill leverages semantic search to retrieve relevant memories based on natural language queries, ensuring that agents can access the right information at the right time. Whether it is sharing knowledge between different agents or maintaining a private memory bank for specific tasks, Central Intelligence transforms transient interactions into a continuous, evolving knowledge base.
Central Intelligence Use Cases
- Storing user preferences like preferred programming languages or UI themes to ensure consistency in future interactions.
- Recording significant project decisions or architectural choices to prevent repetitive questioning or conflicting advice.
- Sharing non-sensitive insights between different agents within the same organization to create a unified intelligence layer.
- Recalling debugging insights and past fixes to accelerate troubleshooting in subsequent development sessions.
How Central Intelligence Works
- Store: The agent identifies a valuable insight and uses the remember command to save it to the persistent memory service.
- Index: The content is indexed and stored with specific tags and scopes (agent, user, or org) using Openclaw Skills integration.
- Query: When context is needed, the agent performs a natural language search via the recall command to find semantically similar memories.
- Rank: The service returns a list of memories ranked by similarity scores, allowing the agent to integrate relevant past context into the current prompt.
- Maintain: Outdated or incorrect memories are removed using the forget command to keep the knowledge base accurate and lean.
Central Intelligence Setup
To use this within the Openclaw Skills framework, you must obtain an API key from the Central Intelligence website and set it as an environment variable.
# Set your API key
export CI_API_KEY="your_api_key_here"
All requests are authenticated via a Bearer token in the header and communicate with the API base at [https://central-intelligence-api.fly.dev](https://central-intelligence-api.fly.dev).
Central Intelligence Data Schema & Taxonomy
Central Intelligence organizes data using a structured JSON format to ensure high searchability and metadata tracking.
| Field | Type | Description |
|---|---|---|
id |
UUID | Unique identifier for the specific memory. |
content |
String | The actual text or insight being stored. |
tags |
Array | Categorical labels for organization (e.g., "preferences", "arch"). |
scope |
String | Visibility level: agent, user, or org. |
similarity |
Float | The semantic relevance score returned during recall. |
created_at |
Timestamp | ISO 8601 date of when the memory was created. |
Central Intelligence Advanced Features
- Semantic Search: Uses vector-based retrieval to find memories based on meaning rather than just keyword matching.
- Multi-Level Scoping: Manage privacy and knowledge sharing by promoting memories from individual agent scope to user or organization-wide visibility.
- Context Loading: Batch-retrieve up to 10 relevant memories at the start of a session to instantly ground the agent in project history.
- Tag-Based Filtering: Highly granular organization allowing agents to filter knowledge by specific technical domains or projects.
SKILL.md
Loading
Related Openclaw Skills
RAG Accuracy Optimizer
A professional toolkit for optimizing end-to-end accuracy in Retrieval-Augmented Generation (RAG) systems across specialized domains.
Carrier Logistics Index Tracker
An automated data retrieval tool that extracts and analyzes logistics performance indices for carriers across specific regions and dates.
minimax-mcp
A high-performance MCP skill for OpenClaw that provides native MiniMax web search and image understanding with automated fallback protection.
OpenClaw Dashboard Theme Changer
A dynamic theme customization tool that updates OpenClaw Dashboard accent colors and UI variables through a single command or natural language request.
PDF Studio
A professional-grade document engine for creating high-fidelity, print-ready PDFs with advanced layout control and multi-language support.
Context Loader
An advanced context loading skill that retrieves business knowledge networks, object instances, and subgraph relationships for AI agents.
Featured*
