[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-70533":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":9,"totalLinesOfCode":9,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":9,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":9,"rankLanguage":9,"license":9,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":22,"hasPages":22,"topics":24,"createdAt":9,"pushedAt":9,"updatedAt":38,"readmeContent":39,"aiSummary":40,"trendingCount":16,"starSnapshotCount":16,"syncStatus":41,"lastSyncTime":42,"discoverSource":43},70533,"zvec","alibaba\u002Fzvec","alibaba","A lightweight, lightning-fast, in-process vector database",null,"https:\u002F\u002Fgithub.com\u002Falibaba\u002Fzvec","C++",9775,565,49,24,0,18,39,165,54,110.76,false,"main",[25,26,27,28,29,30,31,32,33,34,35,36,37],"rag","agent-skills","embedded","faiss","hnsw","llm-memory","search-engine","semantic-search","similarity-search","vector-database","local","db","vector-db","2026-06-12 04:00:55","\u003Cp align=\"right\">\n  English | \u003Ca href=\".\u002FREADME_CN.md\">中文\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cdiv align=\"center\">\n  \u003Cpicture>\n    \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\"https:\u002F\u002Fzvec.oss-cn-hongkong.aliyuncs.com\u002Flogo\u002Fgithub_log_2.svg\" \u002F>\n    \u003Cimg src=\"https:\u002F\u002Fzvec.oss-cn-hongkong.aliyuncs.com\u002Flogo\u002Fgithub_logo_1.svg\" width=\"400\" alt=\"zvec logo\" \u002F>\n  \u003C\u002Fpicture>\n\u003C\u002Fdiv>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fcodecov.io\u002Fgithub\u002Falibaba\u002Fzvec\">\u003Cimg src=\"https:\u002F\u002Fcodecov.io\u002Fgithub\u002Falibaba\u002Fzvec\u002Fgraph\u002Fbadge.svg?token=O81CT45B66\" alt=\"Code Coverage\"\u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Falibaba\u002Fzvec\u002Factions\u002Fworkflows\u002F01-ci-pipeline.yml\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Falibaba\u002Fzvec\u002Factions\u002Fworkflows\u002F01-ci-pipeline.yml\u002Fbadge.svg?branch=main\" alt=\"Main\"\u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Falibaba\u002Fzvec\u002Fblob\u002Fmain\u002FLICENSE\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-Apache%202.0-blue.svg\" alt=\"License\"\u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fpypi.org\u002Fproject\u002Fzvec\u002F\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Fzvec.svg\" alt=\"PyPI Release\"\u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fpypi.org\u002Fproject\u002Fzvec\u002F\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fpython-3.10%20~%203.14-blue.svg\" alt=\"Python Versions\"\u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002F@zvec\u002Fzvec\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fnpm\u002Fv\u002F@zvec\u002Fzvec.svg\" alt=\"npm Release\"\u002F>\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Ftrendshift.io\u002Frepositories\u002F20830\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Ftrendshift.io\u002Fapi\u002Fbadge\u002Frepositories\u002F20830\" alt=\"alibaba%2Fzvec | Trendshift\" style=\"width: 250px; height: 55px;\" width=\"250\" height=\"55\"\u002F>\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fzvec.org\u002Fen\u002Fdocs\u002Fdb\u002Fquickstart\u002F\">🚀 \u003Cstrong>Quickstart\u003C\u002Fstrong> \u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fzvec.org\u002Fen\u002F\">🏠 \u003Cstrong>Home\u003C\u002Fstrong> \u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fzvec.org\u002Fen\u002Fdocs\u002Fdb\u002F\">📚 \u003Cstrong>Docs\u003C\u002Fstrong> \u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fzvec.org\u002Fen\u002Fdocs\u002Fdb\u002Fbenchmarks\u002F\">📊 \u003Cstrong>Benchmarks\u003C\u002Fstrong> \u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fdeepwiki.com\u002Falibaba\u002Fzvec\">🔎 \u003Cstrong>DeepWiki\u003C\u002Fstrong> \u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002FrKddFBBu9z\">🎮 \u003Cstrong>Discord\u003C\u002Fstrong> \u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fx.com\u002FZvecAI\">🐦 \u003Cstrong>X (Twitter)\u003C\u002Fstrong> \u003C\u002Fa>\n\u003C\u002Fp>\n\n**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.\n\n> [!Important]\n> 🚀 **v0.4.0 (May 9, 2026)**\n>\n> - **Dart\u002FFlutter SDK**: Published the official [zvec](https:\u002F\u002Fgithub.com\u002Fzvec-ai\u002Fzvec-dart) Flutter package with FFI bindings. Supports Android (arm64-v8a) and iOS (arm64) — no manual native compilation required.\n> - **iOS Build Support**: Added support for building on iOS platforms, expanding cross-platform coverage.\n> - **Enlarged topK Limit**: Relaxed the upper bound on topK to support larger-scale recall scenarios.\n> - **Bug Fixes**: SQ8 quantizer recall drop; Windows path handling; sparse vector index ordering.\n>\n> 👉 [Read the Release Notes](https:\u002F\u002Fgithub.com\u002Falibaba\u002Fzvec\u002Freleases\u002Ftag\u002Fv0.4.0) | [View Roadmap 📍](https:\u002F\u002Fgithub.com\u002Falibaba\u002Fzvec\u002Fissues\u002F309)\n\n## 💫 Features\n\n- **Blazing Fast**: Searches billions of vectors in milliseconds.\n- **Simple, Just Works**: [Install](#-installation) and start searching in seconds. Pure local, no servers, no config, no fuss.\n- **Dense + Sparse Vectors**: Work with both dense and sparse embeddings, with native support for multi-vector queries in a single call.\n- **Hybrid Search**: Combine semantic similarity with structured filters for precise results.\n- **Durable Storage**: Write-ahead logging (WAL) guarantees persistence — data is never lost, even on process crash or power failure.\n- **Concurrent Access**: Multiple processes can read the same collection simultaneously; writes are single-process exclusive.\n- **Runs Anywhere**: As an in-process library, Zvec runs wherever your code runs — notebooks, servers, CLI tools, or even edge devices.\n\n## 📦 Installation\n\n### [Python](https:\u002F\u002Fpypi.org\u002Fproject\u002Fzvec\u002F)\n\n**Requirements**: Python 3.10 - 3.14\n\n```bash\npip install zvec\n```\n\n### [Node.js](https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002F@zvec\u002Fzvec)\n\n```bash\nnpm install @zvec\u002Fzvec\n```\n\n### ✅ Supported Platforms\n\n- Linux (x86_64, ARM64)\n- macOS (ARM64)\n- Windows (x86_64)\n\n### 🛠️ Building from Source\n\nIf you prefer to build Zvec from source, please check the [Building from Source](https:\u002F\u002Fzvec.org\u002Fen\u002Fdocs\u002Fdb\u002Fbuild\u002F) guide.\n\n## ⚡ One-Minute Example\n\n```python\nimport zvec\n\n# Define collection schema\nschema = zvec.CollectionSchema(\n    name=\"example\",\n    vectors=zvec.VectorSchema(\"embedding\", zvec.DataType.VECTOR_FP32, 4),\n)\n\n# Create collection\ncollection = zvec.create_and_open(path=\".\u002Fzvec_example\", schema=schema)\n\n# Insert documents\ncollection.insert([\n    zvec.Doc(id=\"doc_1\", vectors={\"embedding\": [0.1, 0.2, 0.3, 0.4]}),\n    zvec.Doc(id=\"doc_2\", vectors={\"embedding\": [0.2, 0.3, 0.4, 0.1]}),\n])\n\n# Search by vector similarity\nresults = collection.query(\n    zvec.VectorQuery(\"embedding\", vector=[0.4, 0.3, 0.3, 0.1]),\n    topk=10\n)\n\n# Results: list of {'id': str, 'score': float, ...}, sorted by relevance\nprint(results)\n```\n\n## 📈 Performance at Scale\n\nZvec delivers exceptional speed and efficiency, making it ideal for demanding production workloads.\n\n\u003Cimg src=\"https:\u002F\u002Fzvec.oss-cn-hongkong.aliyuncs.com\u002Fqps_10M.svg\" width=\"800\" alt=\"Zvec Performance Benchmarks\" \u002F>\n\nFor detailed benchmark methodology, configurations, and complete results, please see our [Benchmarks documentation](https:\u002F\u002Fzvec.org\u002Fen\u002Fdocs\u002Fdb\u002Fbenchmarks\u002F).\n\n## 🤝 Join Our Community\n\n\u003Cdiv align=\"center\">\n\n\u003Cdiv align=\"center\">\n\n| 💬 DingTalk | 📱 WeChat | 🎮 Discord | X (Twitter) |\n| :---: | :---: | :---: | :---: |\n| \u003Cimg src=\"https:\u002F\u002Fzvec.oss-cn-hongkong.aliyuncs.com\u002Fqrcode\u002Fdingding.png\" width=\"150\" alt=\"DingTalk QR Code\"\u002F> | \u003Cimg src=\"https:\u002F\u002Fzvec.oss-cn-hongkong.aliyuncs.com\u002Fqrcode\u002Fwechat.png?v=6\" width=\"150\" alt=\"WeChat QR Code\"\u002F> | [![Discord](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDiscord-Join%20Server-5865F2?style=for-the-badge&logo=discord&logoColor=white)](https:\u002F\u002Fdiscord.gg\u002FrKddFBBu9z) | [![X (formerly Twitter) Follow](https:\u002F\u002Fimg.shields.io\u002Ftwitter\u002Ffollow\u002FZvecAI)](\u003Chttps:\u002F\u002Fx.com\u002FZvecAI>) |\n| Scan to join | Scan to join | Click to join | Click to follow |\n\n\u003C\u002Fdiv>\n\n\u003C\u002Fdiv>\n\n## ❤️ Contributing\n\nWe welcome and appreciate contributions from the community! Whether you're fixing a bug, adding a feature, or improving documentation, your help makes Zvec better for everyone.\n\nCheck out our [Contributing Guide](.\u002FCONTRIBUTING.md) to get started!\n","zvec 是一个轻量级、超快速的进程内向量数据库，专为直接嵌入应用程序而设计。该项目采用C++编写，具备生产级别的低延迟和可扩展性相似性搜索能力，支持最小化配置即可实现高效的数据处理。特别适合需要实时或近实时处理大规模向量数据的应用场景，如推荐系统、图像检索等。此外，zvec 还提供了对多种编程语言的支持，包括Python、Dart\u002FFlutter等，使得开发者能够更灵活地将其集成到不同平台上的项目中。",2,"2026-06-11 03:32:42","trending"]