vectorize-search

Index plaintext content and store embeddings for semantic search over encrypted memories.

22|4|Updated Feb 7, 2026

Search Tags:#embeddings #cloudflare #vectorize #semantic-search #vector-database #memory-retrieval

Ready to run

npx skills add https://github.com/joelhooks/atproto-agent-network --skill vectorize-search

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: vectorize-search
Source: https://github.com/joelhooks/atproto-agent-network/tree/main/.agents/skills/vectorize-search
Command: npx skills add https://github.com/joelhooks/atproto-agent-network --skill vectorize-search

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Vectorize enables semantic search over encrypted memories by indexing plaintext content and storing embeddings with record IDs.

Core Features & Use Cases

Embed text to create dense representations for fast similarity search.
Upsert and query vector indexes against agent memory with metadata filters.
Use case: Retrieve relevant memories by querying with natural language.

Quick Start

Create a vector index for agent memory and run a semantic search against a query to retrieve matching records.

Frequently Asked Questions about vectorize-search

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

FAQPage Schema

How do I implement semantic search over encrypted memories?▼

Semantic search over encrypted memories is implemented by indexing plaintext content and storing generated embeddings with record IDs in a vector index. A workflow then decrypts the retrieved results after the search is performed.

How does Vectorize handle agent memory retrieval with metadata filters?▼

Vectorize enables agent memory retrieval by upserting and querying vector indexes using metadata filters. This allows targeted recall of relevant memories by querying the index with natural language across a federated network.

Do I need an embedding model to use Cloudflare Vectorize for similarity search?▼

Yes, an embedding model is required to embed text into dense representations for similarity search. You also need a Vectorize index and a workflow to handle the encrypted memory retrieval process.

How do I retrieve relevant memories by querying with natural language?▼

You can retrieve relevant memories by running a semantic search against a natural language query. The system matches the query against dense vector representations stored in the index to return matching records.

When should I not use a vector database for memory recall?▼

You should avoid using a vector database for memory recall if your workflow cannot decrypt results after retrieval or if you lack an embedding model to generate the dense representations required for indexing plaintext content.