A local retrieval skill that utilizes SQLite for hybrid vector and keyword search across massive documentation libraries without bloating agent memory.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install literag
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 literag 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 LiteRAG?
LiteRAG is a specialized local retrieval skill designed to handle large-scale documentation corpora that are too massive or noisy for a standard AI agent's main memory. By leveraging independent SQLite databases for each knowledge library, it enables high-performance hybrid search functionality that combines full-text keywords with vector embeddings. This allows your tools to access extensive technical references, such as the Blender manual or complex API documentation, while maintaining a clean and efficient primary workspace.
Built for developers who require precision and speed, this skill provides a robust framework for indexing, searching, and inspecting external data sources. As one of the more technical Openclaw Skills, it ensures that your AI agent has access to the right information at the right time without the performance degradation associated with oversized context windows.
LiteRAG Use Cases
- Searching through massive external documentation sets like the Blender manual or Python API references.
- Indexing and querying large framework SDKs, product documentation, or technical blog archives.
- Retrieving specific information from exported Markdown document sets without polluting the main memory index.
- Benchmarking retrieval quality and ranking across various large-scale technical datasets.
How LiteRAG Works
- Define the target documentation library and its source root within the workspace configuration file.
- Execute the indexing process to create a local SQLite database containing vector embeddings and full-text search indexes.
- Perform a hybrid search query to retrieve grouped document hits based on both semantic meaning and keyword matches.
- Inspect specific search results by file path and chunk range to provide the AI agent with precise, high-quality context.
- Use the status and meta commands to monitor index health and ensure the retrieval system is optimized for current data.
LiteRAG Setup
To get started with LiteRAG, first install the necessary Python dependencies within your environment:
python3 -m pip install -r {baseDir}/requirements.txt
Next, configure your knowledge libraries in the <workspace>/.literag/knowledge-libs.json file. Once configured, you can index a library using the following command:
/literag index <library_name>
LiteRAG Data Schema & Taxonomy
LiteRAG organizes its data and metadata within the .literag/ directory of your workspace for portability and isolation:
| Component | Description |
|---|---|
knowledge-libs.json |
The central configuration file defining library names, paths, and search settings. |
.sqlite databases |
Individual database files for each library containing metadata, FTS indexes, and vector embeddings. |
scripts/ |
A collection of Python utilities for indexing, searching, and benchmarking performance. |
references/ |
Contains detailed playbooks for optimization, usage examples, and agent-specific prompt templates. |
LiteRAG Advanced Features
- Hybrid retrieval engine that combines SQLite FTS (Full-Text Search) with vector-based similarity.
- Support for local OpenAI-compatible embedding models to ensure data privacy and reduce latency.
- Built-in benchmarking tools to compare retrieval latency and hit accuracy across different query sets.
- Independent library management allowing for discrete, siloed knowledge bases tailored to specific projects.
- Seamless integration with other Openclaw Skills to facilitate advanced RAG (Retrieval-Augmented Generation) workflows.
SKILL.md
Loading
Related Openclaw Skills
OpenClaw Agent Log Skill
An automated evidence preservation and trace management skill designed to capture the full lifecycle of OpenClaw agent activities.
Self-Improving Agent
A universal self-improvement system that enables AI agents to learn from every interaction and autonomously evolve their codebase based on real-world experiences.
Broker Weekly Monitor
A professional-grade financial monitoring tool that automates the tracking of US retail brokerages, market-wide trading volumes, and the emerging crypto and prediction market ecosystems.
Atlas Travel Extras
A comprehensive personal travel assistant for planning trips, tracking budgets, and managing travel documents within a structured environment.
Search Agent
An intelligent AI research assistant that performs multi-source web searches and generates comprehensive, cited summaries.
OSCHINA Technical Publisher
A professional automation tool for drafting, managing, and publishing technical articles on the OSCHINA open-source platform.
Featured*
