Zvec

English | 中文

🚀 Quickstart | 🏠 Home | 📚 Docs | 📊 Benchmarks | 🔎 DeepWiki | 🎮 Discord | 🐦 X (Twitter)

Zvec is an open-source, in-process vector database — lightweight, lightning-fast, and designed to embed directly into applications. Battle-tested within Alibaba Group, it delivers production-grade, low-latency and scalable similarity search with minimal setup.

[!Important] 🚀 v0.7.0 (August 24, 2026)

• zvec-grep (zg): Local-first workspace search that unifies ripgrep, BM25, and vector search behind one CLI — built for humans and AI agents.
• ReMe integration: zvec is now a file store backend in ReMe, the memory management kit for agents, providing in-process HNSW ANN search.
• DiskANN productionization: Adds Linux ARM64 / macOS ARM64 support and an io_uring async I/O backend, with automatic fallback to the best available I/O option — no user intervention needed.
• Index optimization: New IVF-RaBitQ index and PQ-INT8 quantizer; RaBitQ supports runtime AVX2 / AVX512 dispatch, so the same binary automatically picks the best path on each CPU.
• Deployment experience improved: Prebuilt dynamic libraries slimmed significantly (macOS arm64 C API library 37→22 MB, -40%); new musl libc / Alpine Linux support; prebuilt SDK binaries for Linux (glibc/musl), macOS, Windows, Android, and iOS published with every release.
• DocIterator: New iterator for streaming full-collection document traversal across C++, C, and Python.
• Full-text search: New N-gram tokenizer, better suited for phrase, code, and short-text search.

👉 Read the Release Notes | View Roadmap 📍

💫 Features

• Blazing Fast: Searches billions of vectors in milliseconds.
• Simple, Just Works: Install and start searching in seconds. Pure local, no servers, no config, no fuss.
• Dense + Sparse Vectors: Support dense and sparse embeddings, multi-vector queries, and a rich selection of vector index types that scale from memory to disk.
• Full-Text Search (FTS): Native keyword-based full-text search — query string fields with natural-language or structured expressions.
• Hybrid Search: Fuse vector similarity, full-text search, and structured filters in a single query for precise results.
• Durable Storage: Write-ahead logging (WAL) guarantees persistence — data is never lost, even on process crash or power failure.
• Concurrent Access: Multiple processes can read the same collection simultaneously; writes are single-process exclusive.
• Runs Anywhere: As an in-process library, Zvec runs wherever your code runs — notebooks, servers, CLI tools, or even edge devices.

📦 Installation

Zvec offers official SDKs across multiple languages: