OpenViking Memory Provider

Context database by Volcengine (ByteDance) with filesystem-style knowledge hierarchy, tiered retrieval, and automatic memory extraction.

Requirements

pip install openviking
OpenViking server running (openviking-server)
Embedding + VLM model configured in ~/.openviking/ov.conf

Setup

bash

hermes memory setup    # select "openviking"

The setup can link to an existing ~/.openviking/ovcli.conf, copy its current connection values into Hermes, or create a minimal ovcli.conf when one does not exist.

Or manually:

bash

hermes config set memory.provider openviking
echo "OPENVIKING_ENDPOINT=http://localhost:1933" >> ~/.hermes/.env

Config

All config via environment variables in .env:

Env Var	Default	Description
`OPENVIKING_ENDPOINT`	`http://127.0.0.1:1933`	Server URL
`OPENVIKING_API_KEY`	(none)	User/admin API key for authenticated servers
`OPENVIKING_ACCOUNT`	`default`	Tenant account for local/trusted mode
`OPENVIKING_USER`	`default`	Tenant user for local/trusted mode
`OPENVIKING_AGENT`	`hermes`	Hermes peer ID in OpenViking, used for peer-scoped memories

When OPENVIKING_API_KEY is set, Hermes lets OpenViking derive account/user identity from the key. In local or trusted deployments without an API key, Hermes sends OPENVIKING_ACCOUNT and OPENVIKING_USER as identity headers.

Tools

Tool	Description
`viking_search`	Semantic search with fast/deep/auto modes
`viking_read`	Read content at a viking:// URI (abstract/overview/full)
`viking_browse`	Filesystem-style navigation (list/tree/stat)
`viking_remember`	Store a fact for extraction on session commit
`viking_add_resource`	Ingest URLs/docs into the knowledge base