OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Memory & RAG

Seekdb

Seekdb is an AI-oriented database for vector, text, structured and semi-structured data, with hybrid search and SQL access.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Seekdb — OpenViST project profile in Agent Memory & RAG.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Consider Seekdb when an agent or RAG application needs durable state and combined semantic, keyword and structured retrieval in one database.

Who it is for

  • Developers building AI agents with persistent memory
  • Teams implementing retrieval-augmented generation systems
  • Developers using LangChain, LlamaIndex or Dify
  • Engineers needing embedded or server-based database operation

Documented uses

  • Store persistent agent state
  • Retrieve information through vector, full-text and scalar conditions
  • Support RAG applications with one hybrid retrieval engine
  • Create isolated experimental agent workspaces and merge selected changes
Before you choose

Requirements & limits

The project is public and open source under the Apache-2.0 license.

  • Whether one SQL query should combine vector search, full-text search and scalar filtering
  • Whether the application needs embedded as well as server operation
  • Whether MySQL protocol compatibility and ACID transactions fit the existing architecture
  • Whether copy-on-write fork and merge workflows are useful for agent experimentation
  • Whether the chosen application framework is LangChain, LlamaIndex or Dify

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install the Python SDK and try embedded Seekdb

Set up the documented Python entry point for an in-process Seekdb trial.

Before you start

  • Python environment
  • Access to the Seekdb GitHub repository and its Python SDK

Steps

  1. Install or upgrade the SDK with the command below.

    Documented command
    pip install -U pyseekdb

  2. Run the repository's documented 30-second demo from images/demo.py.

  3. Use embedded mode for the in-process trial; the documentation states that server or OceanBase mode can be selected separately.

Expected outcome

A documented starting point for trying Seekdb in embedded mode through its Python SDK.

Guide limitations

  • The available material does not document the demo's full execution output or provide a complete application workflow.
  • The procedure does not establish production suitability or performance for a particular workload.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
1 October 2026
Original website title
oceanbase/seekdb · Official homepage title · retained in its source language
How we review sourcesSuggest a correction