SeekDB

Installation

Choose your platform:

<details open> <summary><b>☁️ Cloud (Zero Install)</b></summary>

One curl, a running database — no signup, no credit card.

curl -X POST https://d0.seekdb.ai/api/v1/instances

Free for 7 days. Learn more →

</details>

<details open> <summary><b>🐍 Python (Recommended for AI/ML)</b></summary>

pip install -U pyseekdb

</details>

<details> <summary><b>🐳 Docker (Quick Testing)</b></summary>

docker run -d \
  --name seekdb \
  -p 2881:2881 \
  -p 2886:2886 \
  -v ./data:/var/lib/oceanbase \
  oceanbase/seekdb:latest

</details>

<details> <summary><b>📦 Binary (Standalone)</b></summary>

```bash

Linux (one-line install, may need sudo)

curl -fsSL https://obportal.s3.ap-southeast-1.amazonaws.com/download-center/opensource/seekdb/seekdb_install.sh | bash

Build from Source

Before building, please install the required toolchain and dependencies for your operating system. See Install Toolchain for detailed instructions.

```bash

🎬 Quick Start

📝 More Examples

For the full Python SDK walkthrough — connection modes, embedding functions, metadata filters — see the pyseekdb User Guide.

<details open> <summary><b>🤖 Agent Memory Pattern (continuous write + immediate retrieval)</b></summary>

The canonical agent loop: write an observation, retrieve relevant context milliseconds later, repeat. seekdb's async index pipeline keeps both sides fast under sustained concurrency.

import pyseekdb

client = pyseekdb.Client(path="./agent_state.db")
memory = client.get_or_create_collection(name="episodic")

for step in agent.run():
    # Persist the observation
    memory.upsert(ids=[step.id], documents=[step.observation])

    # Retrieve relevant context — milliseconds after the write,
    # served by the incremental HNSW (no waiting on a background rebuild)
    relevant = memory.query(query_texts=step.next_query, n_results=5)

    agent.act(relevant)

</details>

<details> <summary><b>🗄️ SQL — Schema + Hybrid Search</b></summary>

-- Table with vector column, full-text index, and HNSW vector index
CREATE TABLE articles (
  id        INT PRIMARY KEY,
  title     TEXT,
  content   TEXT,
  embedding VECTOR(384),
  FULLTEXT INDEX idx_fts (content) WITH PARSER ik,
  VECTOR   INDEX idx_vec (embedding) WITH (DISTANCE=l2, TYPE=hnsw, LIB=vsag)
) ORGANIZATION = HEAP;

-- Hybrid search: vector similarity + full-text match in one query
SELECT id, title,
       l2_distance(embedding, '[0.12, 0.34, ...]') AS dist
FROM articles
WHERE MATCH(content) AGAINST('quarterly report')
ORDER BY dist APPROXIMATE
LIMIT 10;

Python developers can access this via SQLAlchemy or any MySQL driver.

</details>

📚 Use Cases

<details open> <summary><b>🎯 Agentic AI — Memory, Sandbox & State</b></summary>

Agents need a state store that handles continuous memory writes, millisecond-later retrieval, branching for exploration, and rollback when things go wrong. seekdb is built for exactly this:

• Streaming-friendly storage — write a memory, query it in the next ms
• COW sandboxes — FORK DATABASE for safe experimentation, MERGE to accept, DROP to roll back
• Hybrid retrieval — vector + full-text + relational in one SQL
• MySQL protocol — works with LangChain, LlamaIndex, Dify out of the box

Personal assistants · Enterprise automation · Vertical agents · Agent platforms

</details>

<details> <summary><b>🧩 Other Use Cases</b></summary>

seekdb's hybrid retrieval + multi-model engine also fits classic AI workloads:

• 📖 RAG & Knowledge Retrieval — vector + full-text + scalar filters with multi-level access control. Enterprise QA, customer support, industry insights, personal knowledge bases.
• 🔍 Semantic Search — embedding-based search across text, images, and other modalities. Product search, text-to-image, image-to-product.
• 💻 AI-Assisted Coding — semantic code search, multi-project isolation, time-travel queries for IDE plugins and code agents. Local IDEs, web IDEs, design-to-web.
• ⬆️ Enterprise Application Intelligence — MySQL-compatible AI layer for legacy systems, with row/column hybrid storage. Document intelligence, business insights, finance systems.
• 📱 On-Device & Edge AI — embedded / micro-server modes for resource-constrained devices. In-vehicle systems, AI education, companion robots, healthcare devices.

</details>

---

<a id="ecosystem--integrations"></a>

🌟 Ecosystem & Integrations