ai-agent

vearch: Fast Vector Search

Get fast and scalable vector search for AI-native apps with vearch, used by developers.
2,323 stars366 forksPythonGuide quality 8/10Updated 7/27/2026100% free · open source
What it does

Vearch provides fast and scalable vector search capabilities for AI-native applications, allowing developers to efficiently search and retrieve similar vectors in large datasets.

When to use it
  • Building recommendation systems that require fast and accurate similarity searches
  • Developing AI-powered chatbots that need to retrieve relevant information from large knowledge bases
  • Creating image or video search applications that rely on vector embeddings for similarity matching
Ready-to-paste prompt
curl -X POST 'http://localhost:16666/index' -H 'Content-Type: application/json' -d '[{"id":"vec1","vector":[1.0, 2.0, 3.0]}]'}'
Heads up: Vearch requires a compatible version of Go (at least 1.17) to be installed on the system, and the 'vearch server' command must be run with appropriate permissions to bind to the specified port
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/vearch && curl -fsSL https://workflowstacks.com/api/skills/vearch/claude-skill -o ~/.claude/skills/vearch/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How vearch: Fast Vector Search works
Codeflow
Free to inspect

Vearch: Fast Vector Search is a very large Python project (~96k lines across 457 code files, plus 90 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit a month ago, Apache-2.0 license, has a test suite.

Size
Very large codebase
~96k lines · 457 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Go
No API keys detected
Python 32%Go 32%C++ 29%Rust 2%Java 2%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    go.mod
    Dependencies and the commands it exposes
  3. 3
    internal/debugutil/README.md
    Inside internal/ — the main logic begins here
  4. 4
    examples/golang/basic_usage/README.md
    A worked example — copy this to get going
What's in each folder
internal/Core code — the actual logic414 files
api/Backend / API7 files
cmd/Command-line entry points1 files
docs/Documentation10 files
examples/Examples you can copy4 files
sdk/SDKs / client libraries139 files
tools/Helper scripts6 files
cloud/Folder5 files
READMEHas testsDocumentedCI checksExamples includedApache-2.0 licenseUpdated 1 mo ago
Quick Actions
Details
Creator
vearch
Language
Python
Category
ai-agent
Published
5/13/2019

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.