# Pinecone

> Managed vector database for semantic search and agent memory

- Category: Agents & dev (`agents`)
- Official: https://www.pinecone.io/
- Wunderlust: https://wunderlust.xyz/r/pinecone
- Image: https://wunderlust.xyz/media/pinecone-poster.jpg
- Video preview: https://wunderlust.xyz/media/pinecone.webm
- Added: 2026-11-05

## What it is

Pinecone is a managed knowledge retrieval platform for AI, with a vector database, dense and sparse search, metadata filters and namespaces.

## What it’s for

To give an agent or app memory that can be retrieved by semantic search when files and a wiki aren't enough, in RAG, search and recommendation.

## Benefits

- Vector search combined with BM25 text search in the same index
- Managed serverless operation, no capacity planning
- Namespaces for multi-tenancy and metadata filters
- Embedding and reranking models

## Caveats

- Starter, Standard and Enterprise plans with usage-based billing; prices don't appear on the page
- According to the maker, it scales to billions of vectors and updates become searchable in seconds

## Similar on Wunderlust

- [LightRAG](https://wunderlust.xyz/r/lightrag.md): A RAG framework with a knowledge graph and embeddings
- [OpenViking](https://wunderlust.xyz/r/openviking.md): Context database for agents that organizes memory and skills like a file system
- [Gbrain](https://wunderlust.xyz/r/gbrain.md): Second-brain tool for AI agents
- [Netlify](https://wunderlust.xyz/r/netlify.md): Deploy and hosting platform for sites and apps, with publishing via AI agents
- [Supabase](https://wunderlust.xyz/r/supabase.md): Open-source backend platform built on Postgres
- [Alfred](https://wunderlust.xyz/r/alfred.md): Mac launcher with custom searches, snippets and workflows