OpenViking - Context Database for AI Agents
OpenViking is ByteDance's open-source Context Database designed for AI Agents — a next-generation RAG system that replaces flat vector storage with a filesystem paradigm for managing memories, resources, and skills.
Key Features:
- Filesystem paradigm: Organize context like files with URIs (
viking://resources/...
)
- Tiered context (L0/L1/L2): Abstract → Overview → Full content, loaded on demand
- Directory recursive retrieval: Better accuracy than flat vector search
- MCP server included: Full RAG pipeline via Model Context Protocol
Quick Check: Is It Set Up?
test -f ~/code/openviking/examples/mcp-query/ov.conf && echo "Ready" || echo "Needs setup"
curl -s http://localhost:2033/mcp && echo "Running" || echo "Not running"
If Not Set Up → Initialize
Run the init script (one-time):
bash ~/.openclaw/skills/openviking-mcp/scripts/init.sh
This will:
- Clone OpenViking from
https://github.com/volcengine/OpenViking
- Install dependencies with
uv sync
- Create
ov.conf
template
- Pause for you to add API keys (embedding.dense.api_key, vlm.api_key)
Required: Volcengine/Ark API Keys
| Config Key | Purpose |
|---|
embedding.dense.api_key
| Semantic search embeddings |
vlm.api_key
| LLM for answer generation |
Get keys from: https://console.volcengine.com/ark
Start the Server
cd ~/code/openviking/examples/mcp-query
uv run server.py
Options:
--port 2033
- Listen port--host 127.0.0.1
- Bind address--data ./data
- Data directory
Server will be at:
http://127.0.0.1:2033/mcp
Connect to Claude
claude mcp add --transport http openviking http://localhost:2033/mcp
Or add to
~/.mcp.json
:
{
"mcpServers": {
"openviking": {
"type": "http",
"url": "http://localhost:2033/mcp"
}
}
}
Tools Available
| Tool | Description |
|---|
query
| Full RAG pipeline — search + LLM answer |
search
| Semantic search only, returns docs |
add_resource
| Add files, directories, or URLs |
Example Usage
Once connected via MCP:
"Query: What is OpenViking?"
"Search: machine learning papers"
"Add https://example.com/article to knowledge base"
"Add ~/documents/report.pdf"
Troubleshooting
| Issue | Fix |
|---|
| Port in use | uv run server.py --port 2034
|
| Auth errors | Check API keys in ov.conf |
| Server not found | Ensure it's running: curl localhost:2033/mcp
|
Files
ov.conf
- Configuration (API keys, models)data/
- Vector database storageserver.py
- MCP server implementation
