OpenViking Agent工作流

Local Deployment

Prerequisites

Before starting with OpenViking, please ensure your environment meets the following requirements:

• Python Version: 3.10 or higher
• Rust Toolchain: Cargo (Required for building RAGFS and CLI components from source)
• C++ Compiler: GCC 9+ or Clang 11+ (Required for building core extensions)
• Operating System: Linux, macOS, Windows
• Network Connection: A stable network connection is required (for downloading dependencies and accessing model services)

1. Installation

Python Package

pip install openviking --upgrade --force-reinstall

Rust CLI (Optional)

npm i -g @openviking/cli

Or build from source:

cargo install --git https://github.com/volcengine/OpenViking ov_cli

2. Model Preparation

OpenViking requires the following model capabilities:

• VLM Model: For image and content understanding
• Embedding Model: For vectorization and semantic retrieval

Supported VLM Providers

OpenViking supports multiple VLM providers:

Provider-Specific Notes

<details> <summary><b>Volcengine (Doubao)</b></summary>

Volcengine supports both model names and endpoint IDs. Using model names is recommended for simplicity:

{
  "vlm": {
    "provider": "volcengine",
    "model": "doubao-seed-2-0-pro-260215",
    "api_key": "your-api-key",
    "api_base": "https://ark.cn-beijing.volces.com/api/v3"
  }
}

You can also use endpoint IDs (found in Volcengine ARK Console:

{
  "vlm": {
    "provider": "volcengine",
    "model": "ep-20241220174930-xxxxx",
    "api_key": "your-api-key",
    "api_base": "https://ark.cn-beijing.volces.com/api/v3"
  }
}

</details>

<details> <summary><b>OpenAI</b></summary>

Use OpenAI's official API:

{
  "vlm": {
    "provider": "openai",
    "model": "gpt-4o",
    "api_key": "your-api-key",
    "api_base": "https://api.openai.com/v1"
  }
}

You can also use a custom OpenAI-compatible endpoint:

{
  "vlm": {
    "provider": "openai",
    "model": "gpt-4o",
    "api_key": "your-api-key",
    "api_base": "https://your-custom-endpoint.com/v1"
  }
}

</details>

<details> <summary><b>OpenAI Codex (OAuth)</b></summary>

Use this provider when you want OpenViking to call Codex VLM through your ChatGPT/Codex OAuth session instead of a standard OpenAI API key:

```bash openviking-server init

Option 1: Install VikingBot from PyPI (recommended for most users)

pip install "openviking[bot]"

Option 2: Install VikingBot from source (for development)

uv pip install -e ".[bot]"

Server Deployment Details

For production environments, we recommend running OpenViking as a standalone HTTP service to provide persistent, high-performance context support for your AI Agents.

🚀 Deploy OpenViking on Cloud: To ensure optimal storage performance and data security, we recommend deploying on Volcengine Elastic Compute Service (ECS) using the veLinux operating system. We have prepared a detailed step-by-step guide to get you started quickly.

👉 View: Server Deployment & ECS Setup Guide

---

Quick Start

💡 Want to see it in action first? Try OpenViking Studio — a live hosted instance with a context playground, semantic search, and a multi-agent hub. No installation required.

VikingBot Quick Start

VikingBot is an AI agent framework built on top of OpenViking. Here's how to get started:

```bash

OpenViking: The Context Database for AI Agents

English / 中文 / 日本語

<a href="https://www.openviking.ai">Website</a> · <a href="https://openviking.ai/studio">Live Demo</a> · <a href="https://github.com/volcengine/OpenViking">GitHub</a> · <a href="https://github.com/volcengine/OpenViking/issues">Issues</a> · <a href="./docs">Docs</a>

👋 Join our Community

📱 <a href="./docs/en/about/01-about-us.md#lark-group">Lark Group</a> · <a href="./docs/en/about/01-about-us.md#wechat-group">WeChat</a> · <a href="https://discord.com/invite/eHvx8E9XF3">Discord</a> · <a href="https://x.com/openvikingai">X</a>

<a href="https://trendshift.io/repositories/19668" target="_blank"><img src="https://trendshift.io/api/badge/repositories/19668" alt="volcengine%2FOpenViking | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>

</div>

***

✨ May 2026 Update: Updated OpenViking benchmark results across User Memory, Agent Memory, and Knowledge Base QA scenarios. → See Evaluation Highlights.

The OpenViking Solution

OpenViking is an open-source Context Database designed specifically for AI Agents.

We aim to define a minimalist context interaction paradigm for Agents, allowing developers to completely say goodbye to the hassle of context management. OpenViking abandons the fragmented vector storage model of traditional RAG and innovatively adopts a "file system paradigm" to unify the structured organization of memories, resources, and skills needed by Agents.

With OpenViking, developers can build an Agent's brain just like managing local files:

• Filesystem Management Paradigm → Solves Fragmentation: Unified context management of memories, resources, and skills based on a filesystem paradigm.
• Tiered Context Loading → Reduces Token Consumption: L0/L1/L2 three-tier structure, loaded on demand, significantly saving costs.
• Directory Recursive Retrieval → Improves Retrieval Effect: Supports native filesystem retrieval methods, combining directory positioning with semantic search to achieve recursive and precise context acquisition.
• Visualized Retrieval Trajectory → Observable Context: Supports visualization of directory retrieval trajectories, allowing users to clearly observe the root cause of issues and guide retrieval logic optimization.
• Automatic Session Management → Context Self-Iteration: Automatically compresses content, resource references, tool calls, etc., in conversations, extracting long-term memory, making the Agent smarter with use.

Start OpenViking server with Bot enabled

openviking-server --with-bot

3. Knowledge Base QA on HotpotQA

On multi-hop RAG tasks from HotpotQA, increasing OpenViking retrieval from top-5 to top-20 delivers the highest accuracy in this comparison while keeping retrieval latency low:

3.1 Single-turn RAG Across 5 Open-source Datasets

Datasets: FinanceBench, NaturalQuestions, ClapNQ, Qasper, and SyllabusQA. OpenViking reaches 66.87% average accuracy with very low retrieval latency (0.19s), while indexing cost is only 13.8% of LightRAG.

---