How it behaves
The plugin integrates OpenViking at the DeepSeek Harness pre-step stage. Before a step runs, it recalls relevant context and injects a profile. It also captures session activity and provides tools for recalling and writing memory. The upstream summary identifies URI guarding for viking:// resources.
OpenViking represents memories, resources and skills as paths below viking://. Agents can browse this context with ls, tree and find. Retrieval starts with directory context and can move through three content layers:
L0: a short abstract for relevance checks
L1: an overview for planning
L2: the full content, loaded when needed
After a session commits, OpenViking asynchronously extracts user preferences and agent experience into long-term memory.
Data and server boundary
The plugin reads recalled context and profile information from an OpenViking server. Its session-capture and memory-write paths can send session information and memories back to that server. OpenViking organises data under viking://, including user memories, resources and skills. The plugin has a terminal surface and therefore should be evaluated with the terminal permissions available to the agent.
Requirements
An OpenViking server is required as the backend for the recall and write tools. The provided README excerpt does not specify the plugin’s configuration keys, default values, environment variables, server endpoint format, commands for starting the server, or supported platform and version requirements.
Written from the project's own documentation and kept in sync with it. Where the two disagree, the source is authoritative — read the README on GitHub