skills.rest
rockywuest
rockywuestCOMMUNITY
Explore all skills by this author →
𝕏@rockywuestGitHub

memory-qdrant

Search past conversations via vector similarity and match facts from a facts.jsonl file.

3|1|Updated Mar 8, 2026
Search Tags:#knowledge retrieval#semantic search#vector database#memory#qdrant#local
One-click install
npx skills add https://github.com/rockywuest/openclaw-memory-local --skill memory-qdrant
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: memory-qdrant
Source: https://github.com/rockywuest/openclaw-memory-local/tree/main/memory-qdrant
Command: npx skills add https://github.com/rockywuest/openclaw-memory-local --skill memory-qdrant

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides your AI agent with persistent, searchable, and private memory capabilities directly on your local machine, eliminating the need for cloud-based storage and enhancing data privacy.

Core Features & Use Cases

  • Semantic Search: Utilizes Qdrant vector database for intelligent recall of past conversations and information.
  • Fact Verification: Integrates a facts.jsonl file for keyword matching of verified facts, overriding fuzzy recall.
  • Knowledge Routing: Maps keywords to specific knowledge files, guiding the agent to relevant domain-specific information.
  • Use Case: An agent needs to recall specific technical details about a past project. This Skill can semantically search through previous interactions, find exact facts about the project's specifications, and even point to a dedicated knowledge file for in-depth information, all without sending data externally.

Quick Start

Configure the memory-qdrant plugin in your openclaw.json with the path to your facts.jsonl file and any desired knowledge map entries.

Frequently Asked Questions about memory-qdrant

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I add local semantic memory to my AI agent?▼

Local semantic memory is added to an AI agent by using a vector database to store and retrieve past interactions. This Skill utilizes Qdrant to search past conversations via vector similarity directly on your local machine.

Can I verify specific facts without relying on fuzzy semantic search?▼

Fact verification is handled by matching keywords against a dedicated facts.jsonl file. This mechanism overrides fuzzy semantic recall to ensure your agent retrieves precise, verified information.

How does knowledge routing work for domain-specific information?▼

Knowledge routing maps specific keywords to dedicated knowledge files, guiding the agent to relevant domain-specific information. This ensures queries retrieve precise data beyond general conversational recall.

Does local vector database memory require cloud-based storage?▼

Local vector database memory does not require cloud-based storage. This Skill runs entirely on your local machine using Qdrant, maintaining strict data privacy while providing persistent agent memory.

How do I configure memory-qdrant for my agent?▼

You configure memory-qdrant by editing your openclaw.json file. Specify the path to your facts.jsonl file and define any desired knowledge map entries to enable semantic recall and fact verification.

Related Skills

Explore More Software Engineering Skills→
vikrant-projectvikrant-project
2

qdrant-vector-search

Search large datasets using vector similarity with Qdrant.

Community
Advanced
volcenginevolcengine
28.1k

openviking-memory

Capture conversational facts and recall relevant context for AI agents.

Official
Intermediate
smith-hornsmith-horn
75

flow-nexus-swarm

Deploy and manage cloud-based AI agent swarms with Flow Nexus.

Official
Advanced
neuron-coreneuron-core
2.0k

neuron-rag-specialist

Integrate vector stores, embeddings, and document loaders into Neuron AI agents.

Official
Advanced