#32 · Primary category： Vector Databases
Wax
Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple Silicon.. No Server. No API. One File. Pure Swift
Project last updated：08/29/26
GitHub Stars
790
Forks
50
Contributors
10
License
Apache-2.0
Why we included this project
Wax is a Swift vector store that lives in a single .wax file and gives every agent on an Apple Silicon Mac a shared memory. There is no hosted database to stand up: you point Claude, Cursor, Codex, or any MCP client at the local file, and they all read and write to the same store. Because it also ships as a Swift package, you can embed it in an iOS or macOS app and get on-device semantic search over notes, photos, and video without a server or network call. If you run several agents on one machine, this keeps facts and decisions consistent across them, and iCloud or AirDrop sync lets you carry the same memory to another Mac. It is a practical pick for local-first retrieval when you do not want to operate a separate database service.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
supabase
The Postgres development platform. Supabase gives you a dedicated Postgres database to build your web, mobile, and AI applications.
tidb
TiDB is built for agentic workloads that grow unpredictably, with ACID guarantees and native support for transactions, analytics, and vector search. No data silos. No noisy neighbors. No infrastructure ceiling.
milvus
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
qdrant
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
chroma
Search infrastructure for AI