{"repo":"0xnyn/tinkerbird","free":true,"listed":false,"github":"https://github.com/0xnyn/tinkerbird","clone":"git clone https://github.com/0xnyn/tinkerbird.git","description":"Client Side Vector Database","language":"TypeScript","stars":272,"topics":["chrome","hnsw","indexeddb","typescript","vector-database"],"license":"MIT","category":"databases-storage","readme_excerpt":"Examples TinkerBoard TinyChat TinyEmbed TinySonnet TinkerBird is a browser native vector database designed for efficient storage and retrieval of high-dimensional vectors (embeddings). It's query engine, written in TypeScript, leverages HNSW (Hierarchical Navigable Small World) indexes for fast vector retrieval. The storage layer utilizes IndexedDB, which could be extended with an lru-cache. By co-locating data and embeddings, Tikerbird eliminates the roundtrip and reduces reliance on server-side interactions for vector search workloads. With Tinkerbird, sensitive data remains local, thus benefiting from vector search, without the associated cost, compliance and security risks. TinkerBird uses IndexedDB as it's storage layer, which in turn builds upon Blobs and LevelDB storage systems. By using Indexeddb, it benefits from IndexedDB's adoption, stability and familiarity as a native choice for offline first workflows. Pair TinkerBird with TinyLM, its companion client-side inference library for embeddings and text generation — run models like DeepSeek, Llama 3.2, and Nomic Embed directly in the browser with zero-cost WebGPU based inference. Contributing Feel free to contribute to TinkerBird by sending us your suggestions, bug reports, or cat videos. Contributions are what make the open source community such an amazing place to be learn, inspire, and create. Any contributions you make are greatly appreciated . License Distributed under the MIT License. See LICENSE for more inform","default_branch":null,"files":null,"tree":[],"storefront":"/r/0xnyn","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/0xnyn/tinkerbird/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}