A sophisticated research repository skill that enables AI agents to ingest, search, and synthesize knowledge with full source citations.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install lore
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 lore 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 Lore Knowledge Base?
Lore is a dedicated research knowledge repository designed to provide AI agents with a verifiable source of truth. As a key component of the Openclaw Skills library, it allows for the storage of documents, meeting notes, interviews, and technical decisions with full citations. Unlike tools that only store summaries, Lore preserves the original content and links it back to its source, ensuring that every answer provided by an agent is grounded in evidence and retains its original context.
This skill is particularly effective for developers and teams who need to manage large volumes of unstructured data from various sources like Slack, Notion, and GitHub. By utilizing Lore within the Openclaw Skills framework, agents can maintain a persistent memory of project history and user feedback, making them significantly more reliable for long-term project management and decision-making tasks.
Lore Knowledge Base Use Cases
- Preserving meeting notes and interview transcripts for future searchable context.
- Ingesting and centralizing documentation from Slack threads, GitHub issues, and Notion pages.
- Tracking technical decisions and architectural rationales to inform future development cycles.
- Conducting deep research and synthesis across multiple data sources for complex project queries.
- Grounding AI-generated responses in verifiable evidence through linked citations.
How Lore Knowledge Base Works
- Content is identified for preservation from conversations or external system integrations.
- The agent uses the ingest tool to save the content, attaching metadata like source URLs, project names, and participant lists.
- Information is automatically deduplicated to ensure the repository remains clean and efficient.
- When a user asks a question, the agent performs a hybrid, keyword, or semantic search to find relevant context.
- For complex tasks, the agent utilizes the research tool to synthesize findings from multiple documents.
- The agent retrieves the full source text when necessary and presents the answer with clear, clickable citations.
Lore Knowledge Base Setup
To get started with Lore, ensure your environment is configured to use Openclaw Skills and MCP tools.
# Install the lore skill into your agent environment
openclaw install lore
# Configure project-specific tags to organize your knowledge base
openclaw configure lore --project "my-development-project"
Once installed, the agent will have access to the ingest, search, and research tools automatically.
Lore Knowledge Base Data Schema & Taxonomy
Lore organizes knowledge using a structured schema to ensure high-fidelity retrieval and citation.
| Field | Description |
|---|---|
content |
The raw text of the document or note. |
source_url |
A permalink back to the original source (e.g., Slack or Notion). |
source_name |
A human-readable label for the origin of the data. |
project |
The specific project or workspace the content belongs to. |
source_type |
Categorization such as 'meeting', 'decision', or 'transcript'. |
metadata |
Includes additional context like date and participants. |
Lore Knowledge Base Advanced Features
- Idempotent ingestion that prevents data duplication even when the same content is pushed multiple times.
- Multi-mode search capabilities including Semantic (for concepts), Keyword (for identifiers), and Hybrid (for optimal results).
- High-level research synthesis tool for cross-referencing information across diverse documents in the Openclaw Skills ecosystem.
- Insight retention tool specifically designed for short, discrete pieces of knowledge like atomic decisions or requirements.
- Full-text source retrieval ensuring the agent has access to the complete original context when needed.
SKILL.md
Loading
Related Openclaw Skills
Hot Dog or Not — Battle Skill
A competitive food classification skill that pits your AI agent against NVIDIA's Nemotron model to determine if a photo contains a hot dog.
Space Jobs
Search and apply for thousands of space industry jobs across top aerospace companies directly through your AI agent.
Home Assistant Skill
A powerful Python-based bridge for controlling Home Assistant devices, sensors, and scenes via a command-line interface.
Maven Central Publish
A comprehensive toolkit and workflow for publishing Java and Kotlin libraries to Maven Central via the modern Sonatype Central Portal.
Clawstrike Security Audit
A specialized security auditing tool that produces deterministic vulnerability reports and threat models for Openclaw gateway environments.
ClawdStrike
A comprehensive security audit and threat modeling tool designed to verify the integrity and safety of OpenClaw gateway hosts.
Featured*
