# 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.

Repository: https://github.com/oceanbase/seekdb
Canonical: https://ross.abutalabs.com/products/seekdb
Homepage: https://seekdb.ai
Language: C++
License: Apache-2.0
License Family: permissive
Topics: mysql, embedded-database, ai-agents, copy-on-write, full-text-search, hnsw, hybrid-search, langchain, llamaindex, oceanbase, python, rag, sql, vector-databases
Last push: 2026-08-26T08:00:32+00:00

## Health v2 (maintenance only)
Score: 74/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 73, longevity 22
- inputs: {"age_days": 316, "days_push": 7, "days_rel": 100, "gap_med": 42.5, "n_releases_24m": 5}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2882, forks 319 (observed 2026-08-28T04:07:28.053261+00:00)

## What it is
seekdb is an AI-native search database from OceanBase that unifies relational, vector, full-text, JSON, and GIS data in a single MySQL-compatible engine. It supports embedded and client/server deployment, hybrid search (vector + keyword + relational in one SQL query), and in-database AI functions like embedding, reranking, and LLM completion.

## Use cases
- store and search embeddings for RAG applications
- hybrid vector and keyword search in one query
- embedded vector database for Python AI agents
- agent memory and state storage
- MySQL-compatible database with vector search
- build knowledge bases with automatic embeddings
- run in-database LLM inference and reranking via SQL

## When to choose
- you need vector, full-text, and relational search unified in one engine
- you want an embedded, lightweight vector DB for prototyping or agent apps
- you prefer SQL and MySQL ecosystem compatibility over a separate vector store
- you're building RAG pipelines with LangChain, LlamaIndex, or Dify

## When to avoid
- you need a distributed, horizontally scalable database (seekdb doesn't support distributed mode)
- you require in-place upgrades between minor versions, which are currently unsupported
- you need embedded mode on Windows, which is not yet supported
- you need battle-tested production stability at very large scale

## Facets
- artifact type: application
- maturity: active
- function: vector-database, search-engine, database, rag, llm-inference
- domain: databases, artificial-intelligence, developer-tools
- platform: windows, python, cpp, rust, self-hosted
- tags: hybrid-search, hnsw, full-text-search, mysql-compatible, embedded-database, agent-memory, copy-on-write, langchain, llamaindex, sql, search, ai-agents, retrieval-augmented-generation, linux, macos, docker

## Member repositories
- oceanbase/seekdb (main) score 74

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:28.053261+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:35:27.306469+00:00, confidence not recorded.
  - readme: https://github.com/oceanbase/seekdb (fetched 2026-08-28T04:07:28.053261+00:00, sha 602347972274)
  - homepage: https://seekdb.ai (fetched 2026-08-29T09:51:15.917599+00:00, sha bf246179e06d)
  - site_page: https://docs.seekdb.ai/docs (fetched 2026-08-29T09:51:15.926851+00:00, sha c3a895b77467)
  - site_page: https://docs.seekdb.ai/seekdb/changelog (fetched 2026-08-29T09:51:15.929058+00:00, sha 51cc8b6684de)
  - site_page: https://docs.seekdb.ai/docs/using-seekdb-in-python-sdk (fetched 2026-08-29T09:51:15.931279+00:00, sha dc3e1c1f0004)
  - site_page: https://docs.seekdb.ai/docs/experience-hybrid-search (fetched 2026-08-29T09:51:15.933276+00:00, sha a7fe11c706ef)
  - site_page: https://docs.seekdb.ai/docs/experience-vector-search (fetched 2026-08-29T09:51:15.935300+00:00, sha fb38aa909fa0)
  - site_page: https://docs.seekdb.ai/docs/experience-ai-function (fetched 2026-08-29T09:51:15.937181+00:00, sha 0761a0401318)
  - site_page: https://docs.seekdb.ai/docs/api-overview (fetched 2026-08-29T09:51:15.939118+00:00, sha 7e2de3c787fd)
  - site_page: https://docs.seekdb.ai/docs/pyseekdb-sdk-get-started (fetched 2026-08-29T09:51:15.940932+00:00, sha 690217cdb636)
- Data as of 2026-08-30T08:39:29.467469+00:00.