rag-wrapper

Wrap agents with Qdrant-backed memory context for persistent recall.

2|Updated Jan 2, 2026
One-click install
npx skills add https://github.com/mindmorass/reflex --skill rag-wrapper
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: rag-wrapper
Source: https://github.com/mindmorass/reflex/tree/main/plugins/reflex/skills/rag-wrapper
Command: npx skills add https://github.com/mindmorass/reflex --skill rag-wrapper

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill wraps any agent with Qdrant-backed memory context to enable persistent recall.

Core Features & Use Cases

  • RAG-backed wrapping: Attach Qdrant context to an agent to provide memory across sessions.
  • Context-aware delegation: Prepend retrieved documents to prompts before task execution.
  • Use Case: Build memory-enabled assistants for multi-step projects that require recalling previous decisions or documents.

Quick Start

Use rag-wrapper to wrap an agent with Qdrant context and then delegate tasks to the wrapped agent.

Frequently Asked Questions about rag-wrapper

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

FAQPage Schema
How do I add persistent memory to an agent using Qdrant?

Wrap your agent with rag-wrapper to attach Qdrant-backed memory context. The wrapper prepends retrieved documents to prompts before delegation, enabling the agent to recall stored project knowledge across sessions without modifying the agent's core logic.

Can I use retrieval-augmented generation to give an agent access to previous decisions?

Yes. RAG-wrapper injects Qdrant-retrieved context into prompts before task execution, allowing agents to reference and build on prior decisions stored in the vector database across multiple sessions.

What do I need to set up before using rag-wrapper?

You need access to a running Qdrant vector store, a target agent to wrap, and a mechanism to feed retrieved context into prompts. The wrapper handles context retrieval and prepending, so no additional dependencies are required.

How does context retrieval work in long-running agent tasks?

The wrapper queries Qdrant for relevant stored documents, prepends matched context to the prompt, and delegates the enriched task to the agent. This enables multi-step projects to retrieve and apply accumulated knowledge automatically across task execution.

Is rag-wrapper suitable for multi-session assistant workflows?

Yes. It's designed for memory-enabled assistants and workflows where agents must retain and reference project knowledge across separate sessions, making it ideal for long-running tasks and iterative decision-making scenarios.