// agents · qdrant/qdrant

qdrant

qdrant é um projeto de agentes de IA de código aberto de qdrant (qdrant/qdrant no GitHub). Tem 34.969 estrelas no GitHub e 2.731 forks, é publicado sob a licença Apache-2.0 e foi atualizado pela última vez no GitHub em 8 de outubro de 2026.

A high-performance vector search engine for next-gen AI.

★ 35,0 mil estrelas⑂ 2,7 mil forksApache-2.0atualizado out 2026
▦ visual: o README deste projeto não inclui nenhuma captura incorporável,
então aqui vai um marcador. O guia abaixo está completo mesmo assim.
// dados do projeto

Dados do projeto

Repositório
qdrant/qdrant
Estrelas no GitHub
34.969
Forks
2.731
Licença
Apache-2.0
Última atualização no GitHub
8 de outubro de 2026
Categoria
Agentes de IA
Tipo de ficha
Guia de instalação completo
Site oficial
Official site
// como funciona

Como funciona

  1. Pick a first task

    Choose one real workload to test the project against.

  2. Download the project

    Clone it locally and read through the getting-started guide.

  3. Wire up dependencies

    Install the stack it needs and set any environment variables.

  4. Run and verify

    Execute the starter example and check results before going further.

// recursos

Por que as pessoas gostam tanto

Hybrid search

Combines vector and keyword search in one query.

HNSW indexing

Fast approximate nearest neighbor queries.

Rust performance

Low-latency, memory-efficient core.

Rich filtering

Payload-based structured filtering alongside vectors.

Cloud option

Managed cloud available alongside self-hosting.

Apache-2.0

Permissive licensing.

Advertisement
// execute você mesmo

Execute você mesmo

  1. Step 1 — Clone the repo

    Download the source and move into the project folder.

    git clone https://github.com/qdrant/qdrant.git
    cd qdrant
  2. Step 2 — Build

    Compile the Rust engine.

    cargo build --release
  3. Step 3 — Run it

    Start the server (Docker is the fastest path per the docs).

    # see docs for the Docker quickstart
    ./target/release/qdrant
// casos de uso

O que você pode criar

  • Add semantic search to an AI product.
  • Build RAG over large document collections.
  • Run image similarity search.
  • Prototype recommendation features quickly.
Advertisement
// perguntas frequentes

Perguntas frequentes

Who maintains Qdrant?

It is maintained by the qdrant organization at qdrant/qdrant, with 2,731 forks. Check the changelog for the latest stable release.

Is Qdrant free to use?

The open-source engine is free under Apache-2.0; the managed cloud is the paid path.

Do I need a paid API to use it?

Self-hosting is free. You only pay if you choose the managed cloud or for the embedding/LLM APIs you call.

How does it compare to other vector databases?

Compare with Milvus, Weaviate, and Chroma on operations, filtering, and scale.

How do I get started?

The Docker quickstart in the docs is the fastest route; load a sample collection and run a search.

// continue explorando

Ferramentas semelhantes

Agentes de IA

gortex

Gortex, in Go — built for high-performance code-intelligence engine for ai agents.

★ 1,9 mil estrelasApache-2.0
Ver o guia →
Agentes de IA

milvus

The cloud-native vector database for planet-scale similarity search.

★ 46,3 mil estrelasApache-2.0
Ver o guia →
Agentes de IA

sglang

High-performance serving for the LLMs that power your agents.

★ 36,9 mil estrelasApache-2.0
Ver o guia →
Agentes de IA

weaviate

Vector search plus structured filtering in one database.

★ 16,9 mil estrelasNOASSERTION
Ver o guia →
Agentes de IA

exa-mcp-server

Exa's MCP server for web search and crawling — give your AI agent a live, high-quality web index.

★ 5,1 mil estrelasMIT
Ver o guia →
Agentes de IA

codebase-memory-mcp

High-performance code intelligence MCP server: your codebase as a persistent knowledge graph

★ 46,1 mil estrelasMIT
Ver o guia →
// alternativas

Alternativas em Agentes de IA

Os outros projetos de Agentes de IA com mais estrelas no catálogo do LibreAI — a lista realista de alternativas se qdrant não for o ideal para você.

  • openclaw★ 391,6 mil

    A personal AI that really does things — on any OS, with your data staying yours.

  • superpowers★ 294,9 mil

    An agentic skills framework & software development methodology that works.

  • ECC★ 275,2 mil

    Agent harness optimization system with skills, memory and security for Claude Code, Codex and more

  • hermes-agent★ 252,0 mil

    The agent that grows with you — a Python framework for adaptive AI agents.

  • deepseek-harness★ 245,5 mil

    DeepSeek's plugin-based agent harness where everything is a plugin.

// mais em agents

Mais em Agentes de IA

Projetos de Agentes de IA próximos no catálogo, os mais próximos em estrelas de qdrant: continue explorando dos dois lados dele.

  • QwenPaw★ 35,5 mil

    Your personal AI assistant — self-host it, chat anywhere, extend everything.

  • ChatDev★ 34,6 mil

    ChatDev — zero-code multi-agent platform (DevAll) for developing everything, from software to research, Apache-2.0

  • sglang★ 36,9 mil

    High-performance serving for the LLMs that power your agents.

  • Anthropic-Cybersecurity-Skills★ 33,8 mil

    817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fr…

  • firecracker★ 37,2 mil

    Secure, fast microVMs that make serverless possible.

  • openclaude★ 33,7 mil

    A Claude Code-style coding agent that runs anywhere and works with almost any model provider

Baixe o qdrant

Grátis e aberto: pegue o código-fonte, dê uma estrela no repositório e comece a criar.