alibaba/zvecPublic

A lightweight, lightning-fast, in-process vector database

AI summary: An open-source, in-process vector database by Alibaba built for lightweight, low-latency similarity search.

Stars
16.3K
+20 today
Forks
1K
Watchers
70
Open issues
44
Open PRs
64
Contributors
~40
Commits
496
Branches
6
Views (30d)
3

C++Apache-2.0Created Dec 5, 2025Last push 3d agoLatest release v0.8.1+37 stars this week+134 this month

Quick answers

What is zvec?
An open-source, in-process vector database by Alibaba built for lightweight, low-latency similarity search.
What does zvec do?
Zvec is an embedded, purely local vector database designed to run entirely in-process alongside your application code, removing the need for a separate database server. Battle-tested internally at Alibaba, it seamlessly combines dense and sparse vector embeddings, native full-text search, and structured filters into unified hybrid queries. It leverages advanced indexing techniques like HNSW, DiskANN, and quantization (such as INT8/INT4 with random rotation) to achieve millisecond latency across billions of vectors. With write-ahead logging for durability and multi-process read concurrency, it scales efficiently from Jupyter notebooks to edge devices and production backends.
Who is zvec for?
Data scientists, AI engineers, and backend developers who need a blazing-fast, embedded vector search engine without the operational overhead of a standalone database cluster. It provides scalable vector database solutions.
How do I get started with zvec?
pip install zvec
How popular is zvec on GitHub?
alibaba/zvec has 16,261 stars and 1,024 forks on GitHub, and gained 37 stars in the last 7 days.
What license does zvec use?
alibaba/zvec is released under the Apache-2.0 license.

Star history

since Jul 28, 2026
05K10K15KJul 2026Sep 2026Oct 2026Nov 2026
16.3K stars as of Nov 18, 2026. Measured daily since Jul 28, 2026; GitHub no longer exposes earlier star timestamps.

Update history

2 recorded
  • Nov 7, 2026New release v0.8.1 (previously v0.8.0).
  • Oct 27, 2026New release v0.8.0 (previously v0.7.0).

Contribution activity

commits per day, last 52 weeks
NovDecJanFebMarAprMayJunJulAugSepOctNovMonWedFri2025-11-23: 0 commits2025-11-24: 0 commits2025-11-25: 0 commits2025-11-26: 0 commits2025-11-27: 0 commits2025-11-28: 0 commits2025-11-29: 0 commits2025-11-30: 0 commits2025-12-01: 0 commits2025-12-02: 0 commits2025-12-03: 0 commits2025-12-04: 0 commits2025-12-05: 0 commits2025-12-06: 0 commits2025-12-07: 0 commits2025-12-08: 0 commits2025-12-09: 0 commits2025-12-10: 0 commits2025-12-11: 0 commits2025-12-12: 0 commits2025-12-13: 0 commits2025-12-14: 0 commits2025-12-15: 0 commits2025-12-16: 0 commits2025-12-17: 0 commits2025-12-18: 0 commits2025-12-19: 0 commits2025-12-20: 0 commits2025-12-21: 0 commits2025-12-22: 0 commits2025-12-23: 0 commits2025-12-24: 0 commits2025-12-25: 0 commits2025-12-26: 0 commits2025-12-27: 0 commits2025-12-28: 0 commits2025-12-29: 0 commits2025-12-30: 4 commits2025-12-31: 3 commits2026-01-01: 0 commits2026-01-02: 0 commits2026-01-03: 0 commits2026-01-04: 1 commit2026-01-05: 0 commits2026-01-06: 1 commit2026-01-07: 0 commits2026-01-08: 2 commits2026-01-09: 3 commits2026-01-10: 0 commits2026-01-11: 0 commits2026-01-12: 3 commits2026-01-13: 0 commits2026-01-14: 0 commits2026-01-15: 1 commit2026-01-16: 0 commits2026-01-17: 0 commits2026-01-18: 0 commits2026-01-19: 1 commit2026-01-20: 0 commits2026-01-21: 1 commit2026-01-22: 1 commit2026-01-23: 0 commits2026-01-24: 0 commits2026-01-25: 0 commits2026-01-26: 7 commits2026-01-27: 3 commits2026-01-28: 0 commits2026-01-29: 1 commit2026-01-30: 3 commits2026-01-31: 0 commits2026-02-01: 0 commits2026-02-02: 4 commits2026-02-03: 5 commits2026-02-04: 1 commit2026-02-05: 0 commits2026-02-06: 3 commits2026-02-07: 0 commits2026-02-08: 0 commits2026-02-09: 4 commits2026-02-10: 2 commits2026-02-11: 0 commits2026-02-12: 3 commits2026-02-13: 3 commits2026-02-14: 0 commits2026-02-15: 1 commit2026-02-16: 1 commit2026-02-17: 0 commits2026-02-18: 0 commits2026-02-19: 0 commits2026-02-20: 1 commit2026-02-21: 0 commits2026-02-22: 0 commits2026-02-23: 0 commits2026-02-24: 0 commits2026-02-25: 5 commits2026-02-26: 2 commits2026-02-27: 3 commits2026-02-28: 7 commits2026-03-01: 0 commits2026-03-02: 0 commits2026-03-03: 2 commits2026-03-04: 4 commits2026-03-05: 1 commit2026-03-06: 0 commits2026-03-07: 1 commit2026-03-08: 0 commits2026-03-09: 4 commits2026-03-10: 1 commit2026-03-11: 3 commits2026-03-12: 4 commits2026-03-13: 2 commits2026-03-14: 0 commits2026-03-15: 0 commits2026-03-16: 6 commits2026-03-17: 2 commits2026-03-18: 4 commits2026-03-19: 3 commits2026-03-20: 1 commit2026-03-21: 0 commits2026-03-22: 0 commits2026-03-23: 5 commits2026-03-24: 2 commits2026-03-25: 2 commits2026-03-26: 1 commit2026-03-27: 3 commits2026-03-28: 0 commits2026-03-29: 0 commits2026-03-30: 3 commits2026-03-31: 2 commits2026-04-01: 1 commit2026-04-02: 6 commits2026-04-03: 2 commits2026-04-04: 0 commits2026-04-05: 0 commits2026-04-06: 0 commits2026-04-07: 7 commits2026-04-08: 0 commits2026-04-09: 1 commit2026-04-10: 2 commits2026-04-11: 0 commits2026-04-12: 0 commits2026-04-13: 1 commit2026-04-14: 3 commits2026-04-15: 1 commit2026-04-16: 5 commits2026-04-17: 2 commits2026-04-18: 0 commits2026-04-19: 2 commits2026-04-20: 3 commits2026-04-21: 3 commits2026-04-22: 0 commits2026-04-23: 2 commits2026-04-24: 2 commits2026-04-25: 0 commits2026-04-26: 0 commits2026-04-27: 0 commits2026-04-28: 1 commit2026-04-29: 2 commits2026-04-30: 1 commit2026-05-01: 0 commits2026-05-02: 0 commits2026-05-03: 0 commits2026-05-04: 0 commits2026-05-05: 0 commits2026-05-06: 0 commits2026-05-07: 2 commits2026-05-08: 2 commits2026-05-09: 1 commit2026-05-10: 0 commits2026-05-11: 1 commit2026-05-12: 5 commits2026-05-13: 3 commits2026-05-14: 1 commit2026-05-15: 0 commits2026-05-16: 0 commits2026-05-17: 0 commits2026-05-18: 2 commits2026-05-19: 3 commits2026-05-20: 0 commits2026-05-21: 3 commits2026-05-22: 0 commits2026-05-23: 1 commit2026-05-24: 1 commit2026-05-25: 0 commits2026-05-26: 3 commits2026-05-27: 2 commits2026-05-28: 0 commits2026-05-29: 3 commits2026-05-30: 0 commits2026-05-31: 0 commits2026-06-01: 3 commits2026-06-02: 10 commits2026-06-03: 7 commits2026-06-04: 2 commits2026-06-05: 1 commit2026-06-06: 0 commits2026-06-07: 0 commits2026-06-08: 7 commits2026-06-09: 5 commits2026-06-10: 4 commits2026-06-11: 2 commits2026-06-12: 1 commit2026-06-13: 0 commits2026-06-14: 0 commits2026-06-15: 1 commit2026-06-16: 1 commit2026-06-17: 4 commits2026-06-18: 0 commits2026-06-19: 0 commits2026-06-20: 0 commits2026-06-21: 0 commits2026-06-22: 6 commits2026-06-23: 5 commits2026-06-24: 4 commits2026-06-25: 1 commit2026-06-26: 5 commits2026-06-27: 0 commits2026-06-28: 0 commits2026-06-29: 1 commit2026-06-30: 0 commits2026-07-01: 3 commits2026-07-02: 2 commits2026-07-03: 1 commit2026-07-04: 0 commits2026-07-05: 0 commits2026-07-06: 2 commits2026-07-07: 2 commits2026-07-08: 2 commits2026-07-09: 4 commits2026-07-10: 6 commits2026-07-11: 0 commits2026-07-12: 0 commits2026-07-13: 4 commits2026-07-14: 2 commits2026-07-15: 1 commit2026-07-16: 2 commits2026-07-17: 2 commits2026-07-18: 0 commits2026-07-19: 1 commit2026-07-20: 2 commits2026-07-21: 1 commit2026-07-22: 0 commits2026-07-23: 0 commits2026-07-24: 1 commit2026-07-25: 0 commits2026-07-26: 0 commits2026-07-27: 4 commits2026-07-28: 2 commits2026-07-29: 2 commits2026-07-30: 1 commit2026-07-31: 0 commits2026-08-01: 0 commits2026-08-02: 0 commits2026-08-03: 2 commits2026-08-04: 3 commits2026-08-05: 3 commits2026-08-06: 1 commit2026-08-07: 3 commits2026-08-08: 0 commits2026-08-09: 0 commits2026-08-10: 5 commits2026-08-11: 7 commits2026-08-12: 4 commits2026-08-13: 7 commits2026-08-14: 1 commit2026-08-15: 0 commits2026-08-16: 0 commits2026-08-17: 3 commits2026-08-18: 4 commits2026-08-19: 1 commit2026-08-20: 1 commit2026-08-21: 3 commits2026-08-22: 0 commits2026-08-23: 0 commits2026-08-24: 3 commits2026-08-25: 2 commits2026-08-26: 2 commits2026-08-27: 3 commits2026-08-28: 1 commit2026-08-29: 0 commits2026-08-30: 0 commits2026-08-31: 0 commits2026-09-01: 0 commits2026-09-02: 3 commits2026-09-03: 1 commit2026-09-04: 3 commits2026-09-05: 0 commits2026-09-06: 0 commits2026-09-07: 2 commits2026-09-08: 4 commits2026-09-09: 4 commits2026-09-10: 3 commits2026-09-11: 2 commits2026-09-12: 1 commit2026-09-13: 0 commits2026-09-14: 3 commits2026-09-15: 5 commits2026-09-16: 4 commits2026-09-17: 5 commits2026-09-18: 2 commits2026-09-19: 0 commits2026-09-20: 1 commit2026-09-21: 2 commits2026-09-22: 1 commit2026-09-23: 2 commits2026-09-24: 1 commit2026-09-25: 0 commits2026-09-26: 0 commits2026-09-27: 0 commits2026-09-28: 1 commit2026-09-29: 1 commit2026-09-30: 0 commits2026-10-01: 0 commits2026-10-02: 0 commits2026-10-03: 0 commits2026-10-04: 0 commits2026-10-05: 0 commits2026-10-06: 0 commits2026-10-07: 0 commits2026-10-08: 0 commits2026-10-09: 1 commit2026-10-10: 0 commits2026-10-11: 0 commits2026-10-12: 0 commits2026-10-13: 1 commit2026-10-14: 1 commit2026-10-15: 0 commits2026-10-16: 2 commits2026-10-17: 0 commits2026-10-18: 0 commits2026-10-19: 7 commits2026-10-20: 3 commits2026-10-21: 5 commits2026-10-22: 0 commits2026-10-23: 0 commits2026-10-24: 0 commits2026-10-25: 0 commits2026-10-26: 1 commit2026-10-27: 1 commit2026-10-28: 1 commit2026-10-29: 1 commit2026-10-30: 3 commits2026-10-31: 0 commits2026-11-01: 1 commit2026-11-02: 3 commits2026-11-03: 5 commits2026-11-04: 3 commits2026-11-05: 2 commits2026-11-06: 4 commits2026-11-07: 0 commits2026-11-08: 0 commits2026-11-09: 1 commit2026-11-10: 0 commits2026-11-11: 1 commit2026-11-12: 3 commits2026-11-13: 2 commits2026-11-14: 0 commits2026-11-15: 0 commits2026-11-16: 1 commit2026-11-17: 0 commits2026-11-18: 0 commits2026-11-19: 0 commits2026-11-20: 0 commits2026-11-21: 0 commits
496 commits in the last yearLessMore

Signals and awards

derived from tracked data
  • Widely adopted

    16,261 stars

  • Permissive license

    Apache-2.0

  • Continuous integration

    Automated checks passing

  • Repeat trending

    7 trending appearances

What zvec does

Zvec is an embedded, purely local vector database designed to run entirely in-process alongside your application code, removing the need for a separate database server. Battle-tested internally at Alibaba, it seamlessly combines dense and sparse vector embeddings, native full-text search, and structured filters into unified hybrid queries. It leverages advanced indexing techniques like HNSW, DiskANN, and quantization (such as INT8/INT4 with random rotation) to achieve millisecond latency across billions of vectors. With write-ahead logging for durability and multi-process read concurrency, it scales efficiently from Jupyter notebooks to edge devices and production backends.

Data scientists, AI engineers, and backend developers who need a blazing-fast, embedded vector search engine without the operational overhead of a standalone database cluster. It provides scalable vector database solutions.

  • In-Process Architecture: Embeds directly into applications without requiring external servers, complex configurations, or network overhead.
  • Hybrid Search Engine: Fuses dense vectors, sparse vectors, structured metadata filters, and native full-text search in a single query.
  • Advanced Quantization: Uses random rotation for INT8/INT4 quantization to distribute variance across dimensions, preserving high recall rates.
  • Group-By Retrieval: Enables retrieving top-K results per specific group (group-by deduplication) rather than just a global top-K list.
  • Durable Storage: Guarantees data persistence using Write-Ahead Logging (WAL), preventing data loss during process crashes or power failures.
  • Multi-Language Full-Text Search: Includes a Unicode UAX #29 tokenizer and Snowball-based stemming pipeline supporting over 34 languages.

Where teams use it

Local RAG Applications

Building Retrieval-Augmented Generation (RAG) pipelines inside desktop applications or edge devices without relying on external cloud vector databases.

Multi-Modal Search

Searching across text and image embeddings simultaneously using hybrid queries that blend vector similarity with exact keyword matches.

Fast Deduplication

Using group-by search capabilities to quickly filter and deduplicate vast datasets based on metadata categories.

Notebook Experimentation

Allowing data scientists to spin up and query billions of vectors directly from Jupyter notebooks with zero infrastructure setup.

Getting started: pip install zvec

README

main branch

English | 中文

zvec logo

Code Coverage Main License Latest Release

alibaba%2Fzvec | Trendshift

🚀 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

🚀 v0.8.0

  • Broader platform support: Added Intel Mac and Windows ARM64 builds, wheels, and SDKs; extended DiskANN to Windows, Android, and iOS, and RaBitQ to Windows x86_64.
  • Chinese FTS ready to use: Embedded the default Jieba dictionary and HMM model, so Chinese tokenization needs no separate dictionary files or path configuration.
  • Lower index build costs: Reduced peak memory during IVF / DiskANN builds and merges, and accelerated HNSW RaBitQ construction through vector reuse and batched lookups. Build and nested training tasks now enforce configured thread limits more strictly.
  • Faster distance computation: Extensively refactored quantizers and distance calculations to benefit multiple quantization types and metrics, with major improvements to INT4 kernels and Linux ARM64 performance.
  • Faster search: Added faster Uniform quantizers and optimized Vamana graph layout and prefetching. Uniform quantization avoids per-point score reconstruction, though a shared min/max range can increase quantization error and reduce recall.
  • Bug fixes and improvements: Added more flexible UTF-8 document IDs up to 1,024 bytes; fixed concurrent reads during segment switches, index rebuilding with deleted rows, and correctness issues in LIKE and floating-point range filters.

👉 Read the Release Notes

💫 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:

SDK Install / Dependency Source
Python pip install zvec Source
Node.js npm install @zvec/zvec Source
Go Installation guide Source
Rust cargo add zvec-rust Source
Java org.zvec:zvec-java (Maven) Source
Dart / Flutter flutter pub add zvec Source

Python requires 64-bit Python 3.10–3.14; Java requires Java 8+.

Searching code or documents? Try zvec-grep (zg) — a local-first search CLI that unifies ripgrep, BM25, and vector search, built for humans and AI agents.

Prefer a visual tool? Try Zvec Studio to browse data and debug queries — no code required.

✅ Cross-Platform Support

Linux · macOS · Windows · Android · iOS

Zvec supports all major platforms — from servers and desktops to mobile devices.
For more details, please see the platform support documentation.

🛠️ Building from Source

If you prefer to build Zvec from source, please check the Building from Source guide.

⚡ One-Minute Python Example

import zvec

# Define collection schema
schema = zvec.CollectionSchema(
    name="example",
    vectors=zvec.VectorSchema("embedding", zvec.DataType.VECTOR_FP32, 4),
)

# Create collection
collection = zvec.create_and_open(path="./zvec_example", schema=schema)

# Insert documents
collection.insert([
    zvec.Doc(id="doc_1", vectors={"embedding": [0.1, 0.2, 0.3, 0.4]}),
    zvec.Doc(id="doc_2", vectors={"embedding": [0.2, 0.3, 0.4, 0.1]}),
])

# Search by vector similarity
results = collection.query(
    zvec.Query(field_name="embedding", vector=[0.4, 0.3, 0.3, 0.1]),
    topk=10
)

# Results: list of {'id': str, 'score': float, ...}, sorted by relevance
print(results)

📈 Performance at Scale

Zvec delivers exceptional speed and efficiency, making it ideal for demanding production workloads.

Zvec Performance Benchmarks

For detailed benchmark methodology, configurations, and complete results, please see our Benchmarks documentation.

🤝 Join Our Community

💬 DingTalk 📱 WeChat 🎮 Discord X (Twitter)
DingTalk QR Code WeChat QR Code Discord X (formerly Twitter) Follow
Scan to join Scan to join Click to join Click to follow

❤️ Contributing

We 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.

Check out our Contributing Guide to get started!

View on GitHub

Recent activity

commits and pull requests

Releases and announcements

16 total
  1. v0.8.1v0.8.1Nov 6, 2026145 downloads

    # 🚀 Zvec v0.8.1 Release Notes ## 📦 New Features + **PQ for HNSW and IVF:** Added PQ4/PQ8 and optional OPQ, covering training, search, persistence, and subsequent updates. ([#833](https://github.com/alibaba/zvec/pull/833)) + **Broader platform support:** Enabled RaBitQ on Linux, macOS, Android, and iOS ARM64, plus Intel Mac. DiskANN now supports Intel Mac and Windows ARM64. ([#832](https://github.com/alibaba/zvec/pull/832), [#874](https://github.com/alibaba/zvec/pull/874)) + **Grouped search in the C API:** Added grouped vector query and result-management APIs. ([#845](https://github.com/alibaba/zvec/pull/845)) ## 🚀 Performance Improvements + **Lower build memory:** Reduced vector copying and temporary storage in DiskANN, IVF, and selected HNSW construction paths. ([#853](https://github.com/alibaba/zvec/pull/853), [#877](https://github.com/alibaba/zvec/pull/877), [#879](https://github.com/alibaba/zvec/pull/879), [#880](https://github.com/alibaba/zvec/pull/880)) + **Faster search and construction:** Improved Flat batch queries, HNSW construction, and FP16 distance calculation, and completed ARM NEON batch-distance kernels. ([#862](https://github.com/alibaba/zvec/pull/86

  2. v0.8.0v0.8.0Oct 21, 2026772 downloads

    # 🚀 Zvec v0.8.0 Release Notes Zvec v0.8.0 brings **faster queries, lower index build costs, and broader platform support**. Quantizer and distance-kernel improvements benefit multiple formats and metrics, with major gains for INT4 and Linux ARM64. This release also reduces peak memory during IVF/DiskANN builds, accelerates HNSW RaBitQ construction, and makes Chinese FTS ready to use with embedded Jieba resources. Platform coverage expands across desktop and mobile, alongside fixes for concurrent reads, index rebuilding, and filtering correctness. ## ⚠️ Breaking Changes and Upgrade Notes + **Jieba global dictionary configuration removed:** Default dictionaries and the HMM model are now embedded in native libraries. Python users must remove `init(jieba_dict_dir=...)` and calls to `set_default_jieba_dict_dir()` / `get_default_jieba_dict_dir()`. The corresponding C configuration accessors, C default-directory APIs, and C++ global configuration field and registration APIs have also been removed. To override the main dictionary, use the field's `FtsIndexParam.extra_params.jieba_dict_dir` or `ZVEC_JIEBA_DICT_DIR`; field configuration takes precedence. Use `user_dict_path` to add bus

  3. v0.8.0-beta2v0.8.0-beta2Oct 20, 2026pre-release62 downloads

    ## What's Changed * refactor: migrate index storage reads to MemoryBlock by @iaojnh in https://github.com/alibaba/zvec/pull/812 * perf(flat): isolate query metadata from segment cache locking by @egolearner in https://github.com/alibaba/zvec/pull/825 * ci: strip debug symbols from Android prebuilt SDK libraries by @chinaux in https://github.com/alibaba/zvec/pull/702 * fix(sqlengine): keep the exact FLOAT and DOUBLE bound in a forward filter by @jak-pan in https://github.com/alibaba/zvec/pull/818 ## New Contributors * @jak-pan made their first contribution in https://github.com/alibaba/zvec/pull/818 **Full Changelog**: https://github.com/alibaba/zvec/compare/v0.8.0-beta...v0.8.0-beta2

  4. v0.8.0-betav0.8.0-betaOct 19, 2026pre-release60 downloads

    ## What's Changed * build(rabitq): upgrade to RaBitQ 0.7 modular targets by @gouyt13 in https://github.com/alibaba/zvec/pull/814 * perf(flat): batch segment locking to fix HNSW RaBitQ build regression by @JalinWang in https://github.com/alibaba/zvec/pull/813 * perf(search): output refined internal IDs directly by @luoxiaojian in https://github.com/alibaba/zvec/pull/821 * fix(ivf): support primary-key brute-force search for filtered queries by @iaojnh in https://github.com/alibaba/zvec/pull/816 * feat(fts): embed default Jieba resources with LZ4 by @egolearner in https://github.com/alibaba/zvec/pull/807 * ci: publish Windows ARM64 wheels and SDK by @JalinWang in https://github.com/alibaba/zvec/pull/824 ## New Contributors * @gouyt13 made their first contribution in https://github.com/alibaba/zvec/pull/814 **Full Changelog**: https://github.com/alibaba/zvec/compare/v0.8.0-alpha...v0.8.0-beta

  5. v0.8.0-alphav0.8.0-alphaOct 16, 2026pre-release53 downloads

    ## What's Changed * feat(tools): support turbo quantizer in core tool set by @richyreachy in https://github.com/alibaba/zvec/pull/684 * perf: batch convert docs to achieve acceleration by @zzlin237 in https://github.com/alibaba/zvec/pull/647 * feat: add Windows ARM64 (MSVC) build support by @Aanerud in https://github.com/alibaba/zvec/pull/352 * chore: update README to v0.7.0 by @chinaux in https://github.com/alibaba/zvec/pull/697 * feat(refine): support configurable flat storage types by @luoxiaojian in https://github.com/alibaba/zvec/pull/677 * perf: improve CRC32C and FP16 runtime dispatch by @richyreachy in https://github.com/alibaba/zvec/pull/700 * fix(build): fix /Z7 /Zi conflict in Debug on Windows by @JalinWang in https://github.com/alibaba/zvec/pull/692 * refactor(turbo): add AVX2/AVX512 SIMD kernels for distance by @richyreachy in https://github.com/alibaba/zvec/pull/687 * feat(turbo): add PQ int4 quantizers and PQFast FastScan support by @zzlin237 in https://github.com/alibaba/zvec/pull/664 * feat(diskann): Add Windows DiskANN support with asynchronous I/O by @iaojnh in https://github.com/alibaba/zvec/pull/625 * feat(turbo): add AVX-512 FP16 distance kernels by

Code frequency

additions and deletions
+295.5K-295.5KWeek of 2025-12-28: +295,461 linesWeek of 2025-12-28: -1,421 linesWeek of 2026-01-04: +333 linesWeek of 2026-01-04: -335 linesWeek of 2026-01-11: +19 linesWeek of 2026-01-11: -13 linesWeek of 2026-01-18: +6,660 linesWeek of 2026-01-18: -6,095 linesWeek of 2026-01-25: +23,355 linesWeek of 2026-01-25: -23,083 linesWeek of 2026-02-01: +533 linesWeek of 2026-02-01: -438 linesWeek of 2026-02-08: +7,312 linesWeek of 2026-02-08: -1,738 linesWeek of 2026-02-15: +7 linesWeek of 2026-02-15: -3 linesWeek of 2026-02-22: +2,827 linesWeek of 2026-02-22: -2,446 linesWeek of 2026-03-01: +2,396 linesWeek of 2026-03-01: -467 linesWeek of 2026-03-08: +9,338 linesWeek of 2026-03-08: -16,315 linesWeek of 2026-03-15: +25,683 linesWeek of 2026-03-15: -4,183 linesWeek of 2026-03-22: +1,870 linesWeek of 2026-03-22: -234 linesWeek of 2026-03-29: +22,968 linesWeek of 2026-03-29: -3,017 linesWeek of 2026-04-05: +758 linesWeek of 2026-04-05: -76 linesWeek of 2026-04-12: +1,258 linesWeek of 2026-04-12: -350 linesWeek of 2026-04-19: +1,299 linesWeek of 2026-04-19: -9,962 linesWeek of 2026-04-26: +10,131 linesWeek of 2026-04-26: -801 linesWeek of 2026-05-03: +1,272 linesWeek of 2026-05-03: -617 linesWeek of 2026-05-10: +30,888 linesWeek of 2026-05-10: -420 linesWeek of 2026-05-17: +575 linesWeek of 2026-05-17: -3,727 linesWeek of 2026-05-24: +5,761 linesWeek of 2026-05-24: -1,157 linesWeek of 2026-05-31: +46,523 linesWeek of 2026-05-31: -5,842 linesWeek of 2026-06-07: +5,735 linesWeek of 2026-06-07: -1,547 linesWeek of 2026-06-14: +1,785 linesWeek of 2026-06-14: -779 linesWeek of 2026-06-21: +5,382 linesWeek of 2026-06-21: -512 linesWeek of 2026-06-28: +1,395 linesWeek of 2026-06-28: -141 linesWeek of 2026-07-05: +7,106 linesWeek of 2026-07-05: -854 linesWeek of 2026-07-12: +4,673 linesWeek of 2026-07-12: -2,272 linesWeek of 2026-07-19: +2,348 linesWeek of 2026-07-19: -62 linesWeek of 2026-07-26: +1,856 linesWeek of 2026-07-26: -403 linesWeek of 2026-08-02: +2,501 linesWeek of 2026-08-02: -759 linesWeek of 2026-08-09: +25,728 linesWeek of 2026-08-09: -2,969 linesWeek of 2026-08-16: +10,752 linesWeek of 2026-08-16: -4,608 linesWeek of 2026-08-23: +22,038 linesWeek of 2026-08-23: -1,690 linesWeek of 2026-08-30: +7,551 linesWeek of 2026-08-30: -930 linesWeek of 2026-09-06: +18,998 linesWeek of 2026-09-06: -3,404 linesWeek of 2026-09-13: +32,273 linesWeek of 2026-09-13: -10,937 linesWeek of 2026-09-20: +5,135 linesWeek of 2026-09-20: -1,537 linesWeek of 2026-09-27: +377 linesWeek of 2026-09-27: -341 linesWeek of 2026-10-04: +1 linesWeek of 2026-10-04: -1 linesWeek of 2026-10-11: +6,097 linesWeek of 2026-10-11: -397 linesWeek of 2026-10-18: +172,790 linesWeek of 2026-10-18: -2,099 linesWeek of 2026-10-25: +4,496 linesWeek of 2026-10-25: -740 linesWeek of 2026-11-01: +28,870 linesWeek of 2026-11-01: -50,357 linesWeek of 2026-11-08: +3,133 linesWeek of 2026-11-08: -1,863 linesWeek of 2026-11-15: +8 linesWeek of 2026-11-15: -0 linesDec 28, 2025Nov 15, 2026
+868.3K lines added, -171.9K removed over the last year.

Commits per week

last 52 weeks
240Week of 2025-11-23: 0 commitsWeek of 2025-11-30: 0 commitsWeek of 2025-12-07: 0 commitsWeek of 2025-12-14: 0 commitsWeek of 2025-12-21: 0 commitsWeek of 2025-12-28: 7 commitsWeek of 2026-01-04: 7 commitsWeek of 2026-01-11: 4 commitsWeek of 2026-01-18: 3 commitsWeek of 2026-01-25: 14 commitsWeek of 2026-02-01: 13 commitsWeek of 2026-02-08: 12 commitsWeek of 2026-02-15: 3 commitsWeek of 2026-02-22: 17 commitsWeek of 2026-03-01: 8 commitsWeek of 2026-03-08: 14 commitsWeek of 2026-03-15: 16 commitsWeek of 2026-03-22: 13 commitsWeek of 2026-03-29: 14 commitsWeek of 2026-04-05: 10 commitsWeek of 2026-04-12: 12 commitsWeek of 2026-04-19: 12 commitsWeek of 2026-04-26: 4 commitsWeek of 2026-05-03: 5 commitsWeek of 2026-05-10: 10 commitsWeek of 2026-05-17: 9 commitsWeek of 2026-05-24: 9 commitsWeek of 2026-05-31: 23 commitsWeek of 2026-06-07: 19 commitsWeek of 2026-06-14: 6 commitsWeek of 2026-06-21: 21 commitsWeek of 2026-06-28: 7 commitsWeek of 2026-07-05: 16 commitsWeek of 2026-07-12: 11 commitsWeek of 2026-07-19: 5 commitsWeek of 2026-07-26: 9 commitsWeek of 2026-08-02: 12 commitsWeek of 2026-08-09: 24 commitsWeek of 2026-08-16: 12 commitsWeek of 2026-08-23: 11 commitsWeek of 2026-08-30: 7 commitsWeek of 2026-09-06: 16 commitsWeek of 2026-09-13: 19 commitsWeek of 2026-09-20: 7 commitsWeek of 2026-09-27: 2 commitsWeek of 2026-10-04: 1 commitsWeek of 2026-10-11: 4 commitsWeek of 2026-10-18: 15 commitsWeek of 2026-10-25: 7 commitsWeek of 2026-11-01: 18 commitsWeek of 2026-11-08: 7 commitsWeek of 2026-11-15: 1 commitsNov 23, 2025Nov 15, 2026
496 commits in the last 52 weeks.

When work happens

weekday and hour
SunMonTueWedThuFriSat036912151821Sun 0:00 — 0 commitsSun 1:00 — 0 commitsSun 2:00 — 0 commitsSun 3:00 — 0 commitsSun 4:00 — 0 commitsSun 5:00 — 0 commitsSun 6:00 — 0 commitsSun 7:00 — 0 commitsSun 8:00 — 0 commitsSun 9:00 — 0 commitsSun 10:00 — 0 commitsSun 11:00 — 1 commitsSun 12:00 — 1 commitsSun 13:00 — 0 commitsSun 14:00 — 1 commitsSun 15:00 — 2 commitsSun 16:00 — 0 commitsSun 17:00 — 1 commitsSun 18:00 — 0 commitsSun 19:00 — 0 commitsSun 20:00 — 1 commitsSun 21:00 — 0 commitsSun 22:00 — 1 commitsSun 23:00 — 0 commitsMon 0:00 — 0 commitsMon 1:00 — 0 commitsMon 2:00 — 0 commitsMon 3:00 — 2 commitsMon 4:00 — 0 commitsMon 5:00 — 0 commitsMon 6:00 — 0 commitsMon 7:00 — 1 commitsMon 8:00 — 1 commitsMon 9:00 — 4 commitsMon 10:00 — 18 commitsMon 11:00 — 7 commitsMon 12:00 — 1 commitsMon 13:00 — 5 commitsMon 14:00 — 15 commitsMon 15:00 — 6 commitsMon 16:00 — 11 commitsMon 17:00 — 9 commitsMon 18:00 — 5 commitsMon 19:00 — 7 commitsMon 20:00 — 10 commitsMon 21:00 — 3 commitsMon 22:00 — 3 commitsMon 23:00 — 1 commitsTue 0:00 — 0 commitsTue 1:00 — 0 commitsTue 2:00 — 0 commitsTue 3:00 — 0 commitsTue 4:00 — 1 commitsTue 5:00 — 0 commitsTue 6:00 — 0 commitsTue 7:00 — 0 commitsTue 8:00 — 0 commitsTue 9:00 — 4 commitsTue 10:00 — 24 commitsTue 11:00 — 10 commitsTue 12:00 — 3 commitsTue 13:00 — 7 commitsTue 14:00 — 13 commitsTue 15:00 — 12 commitsTue 16:00 — 12 commitsTue 17:00 — 8 commitsTue 18:00 — 3 commitsTue 19:00 — 8 commitsTue 20:00 — 4 commitsTue 21:00 — 1 commitsTue 22:00 — 0 commitsTue 23:00 — 4 commitsWed 0:00 — 0 commitsWed 1:00 — 0 commitsWed 2:00 — 0 commitsWed 3:00 — 0 commitsWed 4:00 — 0 commitsWed 5:00 — 1 commitsWed 6:00 — 1 commitsWed 7:00 — 1 commitsWed 8:00 — 0 commitsWed 9:00 — 2 commitsWed 10:00 — 13 commitsWed 11:00 — 14 commitsWed 12:00 — 3 commitsWed 13:00 — 6 commitsWed 14:00 — 14 commitsWed 15:00 — 9 commitsWed 16:00 — 5 commitsWed 17:00 — 1 commitsWed 18:00 — 1 commitsWed 19:00 — 6 commitsWed 20:00 — 6 commitsWed 21:00 — 6 commitsWed 22:00 — 3 commitsWed 23:00 — 1 commitsThu 0:00 — 0 commitsThu 1:00 — 0 commitsThu 2:00 — 0 commitsThu 3:00 — 0 commitsThu 4:00 — 0 commitsThu 5:00 — 0 commitsThu 6:00 — 0 commitsThu 7:00 — 0 commitsThu 8:00 — 2 commitsThu 9:00 — 1 commitsThu 10:00 — 10 commitsThu 11:00 — 9 commitsThu 12:00 — 2 commitsThu 13:00 — 5 commitsThu 14:00 — 11 commitsThu 15:00 — 5 commitsThu 16:00 — 10 commitsThu 17:00 — 9 commitsThu 18:00 — 2 commitsThu 19:00 — 4 commitsThu 20:00 — 7 commitsThu 21:00 — 0 commitsThu 22:00 — 2 commitsThu 23:00 — 3 commitsFri 0:00 — 1 commitsFri 1:00 — 0 commitsFri 2:00 — 0 commitsFri 3:00 — 1 commitsFri 4:00 — 0 commitsFri 5:00 — 0 commitsFri 6:00 — 0 commitsFri 7:00 — 0 commitsFri 8:00 — 1 commitsFri 9:00 — 2 commitsFri 10:00 — 15 commitsFri 11:00 — 9 commitsFri 12:00 — 1 commitsFri 13:00 — 3 commitsFri 14:00 — 9 commitsFri 15:00 — 7 commitsFri 16:00 — 10 commitsFri 17:00 — 12 commitsFri 18:00 — 3 commitsFri 19:00 — 2 commitsFri 20:00 — 1 commitsFri 21:00 — 1 commitsFri 22:00 — 1 commitsFri 23:00 — 0 commitsSat 0:00 — 0 commitsSat 1:00 — 0 commitsSat 2:00 — 0 commitsSat 3:00 — 0 commitsSat 4:00 — 0 commitsSat 5:00 — 0 commitsSat 6:00 — 0 commitsSat 7:00 — 1 commitsSat 8:00 — 0 commitsSat 9:00 — 0 commitsSat 10:00 — 0 commitsSat 11:00 — 3 commitsSat 12:00 — 1 commitsSat 13:00 — 1 commitsSat 14:00 — 1 commitsSat 15:00 — 0 commitsSat 16:00 — 2 commitsSat 17:00 — 2 commitsSat 18:00 — 0 commitsSat 19:00 — 0 commitsSat 20:00 — 0 commitsSat 21:00 — 0 commitsSat 22:00 — 0 commitsSat 23:00 — 0 commits
Commit volume by weekday and hour (UTC). Larger dots mean more commits.
DateListRankStars gained
Feb 23, 2026daily#19+138
Feb 22, 2026daily#11+299
Feb 21, 2026daily#5+298
Feb 18, 2026daily#23+126
Feb 17, 2026daily#4+295
Feb 16, 2026daily#5+323
Feb 15, 2026daily#6+406
  • morluto/rea

    Reverse engineer anything with agents, from app behavior down to native binaries.

    471.6K stars · TypeScript

  • tensorflow/tensorflow

    An Open Source Machine Learning Framework for Everyone

    201.7K stars · C++

  • anthropics/skills

    Public repository for Agent Skills

    198.1K stars · Python

  • DietrichGebert/ponytail

    Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

    195.7K stars · JavaScript

  • Graphify-Labs/graphify

    Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.

    151.2K stars · Python

  • Shubhamsaboo/awesome-llm-apps

    100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.

    145.2K stars · Python