Verified:GitHub

memory-qdrant

Name: memory-qdrant
Availability: InStock
Author: kaifashraff

Stores and recalls semantic memories for OpenClai agents using Qdrant or in-memory mode with Transformers.js embeddings.

Updated Mar 18, 2026

Search Tags:#recall #embeddings #memory #qdrant #semantic-search #transformers

Ready to run

npx skills add https://github.com/kaifashraff/jarvis-research --skill memory-qdrant-kaifashraff

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: memory-qdrant
Source: https://github.com/kaifashraff/jarvis-research/tree/main/skills/memory-qdrant
Command: npx skills add https://github.com/kaifashraff/jarvis-research --skill memory-qdrant-kaifashraff

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

OpenClaw's memory plugin provides local semantic memory by storing and recalling conversations using a vector store (Qdrant) or in-memory mode. It enables context-aware recall and reduces reliance on external services.

Core Features & Use Cases

Semantic search over locally stored memories using Transformers.js embeddings.
In-memory mode (zero config) or persistent storage with Qdrant.
Optional auto-capture of conversations and context-aware recall for proactive AI behavior.
Memory management with optional LRU eviction in memory mode and safe deletion of memories.
Easy integration with memory_store, memory_search, memory_forget tools and CLI.

Quick Start

Use memory_store to save a key detail, then memory_search to retrieve relevant memories for a given query.

Frequently Asked Questions about memory-qdrant

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

FAQPage Schema

How do I store and recall semantic memory locally for AI agents?▼

You can store and recall local semantic memory using a vector-based store like Qdrant or an in-memory mode. It uses Transformers.js to generate embeddings locally, enabling context-aware recall without external services.

Do I need to configure Qdrant to use local semantic memory?▼

No, you do not need to configure Qdrant for basic local semantic memory. The system supports a zero-configuration in-memory mode for offline operation, while persistent storage with Qdrant remains optional for scaling contexts.

How does semantic search over stored memories work with Transformers.js?▼

Semantic search over stored memories works by generating local text embeddings via Transformers.js. These embeddings are stored in a vector database, allowing agents to retrieve relevant historical context based on query similarity.

Can I automatically capture conversations for context-aware recall?▼

Yes, you can automatically capture conversations for context-aware recall. The system supports optional auto-capture of conversations, enabling proactive AI behavior by proactively retrieving relevant memory context.

How do I manage the memory lifecycle and delete stored embeddings?▼

You can manage the memory lifecycle and delete stored embeddings using the memory_forget tool for safe deletion. In memory mode, the system also supports optional LRU eviction to automatically manage storage capacity.

What is the best way to scale semantic memory from personal to team contexts?▼

The best way to scale semantic memory from personal to team contexts is by transitioning from in-memory mode to persistent storage with Qdrant. This scales vector storage while maintaining local embedding generation and categorization.