A sophisticated knowledge graph skill for AI agents to store entities, define relationships, and perform semantic searches via the SwarmRecall API.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install swarmrecall-knowledge
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 swarmrecall-knowledge 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 SwarmRecall Knowledge?
SwarmRecall Knowledge enables AI agents to move beyond simple flat memory by building complex, structured knowledge graphs. By utilizing this Openclaw Skills integration, agents can create distinct entities—such as people, projects, or abstract concepts—and establish meaningful relations between them. This allows for deep contextual discovery and a more organized representation of information than standard memory systems.
Built on a foundation of PostgreSQL and pgvector, this skill provides robust persistence and semantic search capabilities. It is designed to help developers create agents that remember not just what was said, but how every piece of information relates to the larger picture within the Openclaw Skills ecosystem. The system ensures data privacy through tenant isolation and secure HTTPS communication.
SwarmRecall Knowledge Use Cases
- Mapping organizational structures and project dependencies for enterprise agents.
- Maintaining long-term user context and personal preferences across multiple sessions.
- Semantic discovery of related concepts using vector-based search queries.
- Collaborative knowledge sharing between multiple autonomous agents via shared pools.
- Automatically extracting and linking new information during agent dreaming cycles.
How SwarmRecall Knowledge Works
- The agent authenticates using the SWARMRECALL_API_KEY environment variable as a Bearer token.
- When new information is encountered, the agent creates entities using the REST API, assigning types and properties.
- The agent links these entities by creating relations, forming a graph that represents the logical connections between data points.
- During retrieval, the agent can perform semantic searches or graph traversals to explore connections and find relevant context.
- Periodic validation and dreaming operations maintain graph health by merging duplicates and cleaning up orphaned relations.
SwarmRecall Knowledge Setup
To get started with this skill, ensure your environment is configured correctly. If you already have a key, set it in your environment:
export SWARMRECALL_API_KEY='your_api_key_here'
If the key is not set, the agent can self-register by making a POST request to the registration endpoint. Once registered, the agent should inform the user to visit swarmrecall.ai/claim with the provided claim token to manage the agent data within the Openclaw Skills framework.
SwarmRecall Knowledge Data Schema & Taxonomy
| Component | Description |
|---|---|
| Entities | Nodes representing objects or concepts with specific types and metadata. |
| Relations | Directed links between entities defining the relationship (e.g., works_on). |
| Properties | Flexible JSON objects stored within entities or relations for additional data. |
| Pool ID | An optional UUID used to share knowledge across different agents. |
| Vector Embeddings | Semantic representations stored in pgvector for high-accuracy search. |
SwarmRecall Knowledge Advanced Features
- Shared Pools: Collaborative knowledge bases where multiple agents can read and write shared entities.
- Dreaming Integration: Automated processes to identify similar entities for merging and archive management.
- Graph Traversal: Recursive searching through the graph to a specified depth for complex discovery.
- Tenant Isolation: Strict data separation by owner and agent ID to ensure privacy.
- Semantic Search: High-performance vector search to find entities based on meaning rather than just keywords.
SKILL.md
Loading
Related Openclaw Skills
SwarmRecall Memory
SwarmRecall Memory provides AI agents with persistent, semantic memory and session tracking through a vector-embedded storage API.
Sequential Thinking AI Agent Skill
A sophisticated task decomposition tool based on the MCP Sequential Thinking Server designed to break down complex problems into manageable reasoning steps.
SwarmRecall Skills
SwarmRecall Skills is a centralized registry that allows AI agents to track their capabilities and receive intelligent, context-aware suggestions for task-relevant tools.
10,000 Year Clock Thinking
A cognitive framework for AI agents to evaluate decisions across millennia, fostering long-term resilience and civilization-scale perspective.
HKO Weather (Traditional Chinese)
A specialized weather skill providing real-time Hong Kong Observatory data and 9-day forecasts in Traditional Chinese.
Cleaning & Maintenance - TIDY
An AI agent skill for programmatic scheduling of cleaning services and property maintenance via the TIDY API.
Featured*
