GH Repository · oceanbase
seekdb
The AI-Native Search Database. Best for agent storage, it unifies vector, text, structured, and semi-structured data into a single engine. This all-in-one database makes agents smarter, easier to run, and more stable.
- stars
- 2,934
- 30-day movement
- +83/day
- Related entries
- 60
- Connections
- 3
agent-appC++vector-databasesembedded-databaseai-agentsfull-text-searchcopy-on-writepythonhnswmysqlhybrid-searchlangchainsqlragllamaindexoceanbase
seekdb is an AI-native search database from the OceanBase team that combines vector, full-text, structured, and semi-structured data in a single embedded engine. It exposes SQL and MySQL compatibility, HNSW vector indexes, hybrid search, and Python integrations with LangChain and LlamaIndex for RAG and agent storage.
You need one database to store and query the mixed vector, text, and structured data an agent or RAG pipeline produces.
Use it to
- Store agent memory and session state
- Build RAG pipelines with hybrid vector and full-text search
- Embed alongside a Python application using LangChain or LlamaIndex
- Query vectors and structured data with SQL
- Run an embedded MySQL-compatible database locally
For Developers building AI agents and RAG applications
- Role
- agent-app
- Language
- C++
- Licence
- Apache-2.0
- Forks
- 336
- Open issues
- 327
- Last push
- 2026-09-15
- Latest release
- v1.0.0 · 2025-11-13
topicsvector-databasehybrid-searchai-agentsragembedded-databasesql