wizenheimer/tinkerbird
Client Side Vector Database
Implements HNSW (Hierarchical Navigable Small World) indexing for fast approximate nearest neighbor search, with IndexedDB as the persistent storage layer. Pairs with TinyLM for end-to-end browser-based inference and retrieval, enabling sensitive data to remain local while eliminating server roundtrips for vector workloads. Designed for offline-first applications with zero external dependencies for embedding generation and search.
272 stars and 9 monthly downloads. No commits in the last 6 months. Available on npm.
Stars
272
Forks
14
Language
TypeScript
License
MIT
Category
Last pushed
Sep 28, 2025
Monthly downloads
9
Commits (30d)
0
Dependencies
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/wizenheimer/tinkerbird"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
pixeltable/pixeltable
Data Infrastructure providing a declarative, incremental approach for multimodal AI workloads.
activeloopai/deeplake
Database for AI. Store Vectors, Images, Texts, Videos, etc. Use with LLMs/LangChain. Store,...
superlinked/VectorHub
VectorHub is a free, open-source learning website for people (software developers to senior ML...
hhblaze/DBreeze
C# .NET NOSQL ( key value, object store embedded TextSearch SemanticSearch Vector layer ) ACID...
nitaiaharoni1/vector-storage
Vector Storage is a vector database that enables semantic similarity searches on text documents...