volcengine/OpenViking#examples/dsh-memory-plugin
OpenViking memory and context bundle for DeepSeek Harness: pre-step auto-recall and profile injection, session capture, `viking://` URI guarding, and recall/write memory tools backed by an OpenViking server.
Install
via npm
Resolves a published tarball rather than cloning the repository, and installs without any extra setup. Swap `web` for your profile name if you run another one.
What happened when we ran it
Installed cleanly when we ran it
Every command here is run in a throwaway container against a clean profile, and the result is whatever the harness recorded — not a guess from the source. Last run 24d ago.
Show it in your README
For maintainers: the badge serves this listing's latest sandbox verdict, so a re-run updates it on its own — and it links readers to the full result here.
Due diligence
What it is — dsh-memory-plugin is an OpenViking memory and context bundle plugin.
Who it is for — When you use the DSH plugin system, people who need OpenViking memory and context bundle are suitable to install dsh-memory-plugin. For people who do not need OpenViking as context database, they can use other plugins.
Watch out — Sandbox test passed, installed in a fresh profile and registered into profile by harness. It will execute shell commands. No obvious pitfalls found.
The verdict — I would install it because it can be registered by harness after installation in a fresh profile.
Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.
dsh-memory-plugin is a DeepSeek Harness plugin that connects an agent to an OpenViking server for persistent memory and context retrieval. It adds pre-step processing that automatically recalls relevant context and injects a user profile, captures session data, guards viking:// URIs, and exposes memory recall and write tools.
OpenViking stores memories, resources and skills in a virtual viking:// filesystem. Its retrieval model can browse with ls, tree and find, inspect directory-level L0 abstracts and L1 overviews, then load L2 details when needed. After a session is committed, OpenViking can asynchronously extract user preferences and agent experience into long-term memory. The plugin therefore reads context from the OpenViking server and may write captured session information and extracted memories there.
dsh-memory-plugin is intended for agents that need cross-session user memory or OpenViking’s filesystem-style context model. It is not a self-contained memory store: an OpenViking server is required, and the README excerpt does not document plugin-specific configuration or setup values. The plugin also has a terminal surface, so it runs with the agent’s available terminal permissions; this matters when installing it in an agent that can access local files or execute commands.
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 checksL1: an overview for planningL2: the full content, loaded when neededAfter a session commits, OpenViking asynchronously extracts user preferences and agent experience into long-term memory.
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.
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
Same category
vectorize-io
Hindsight, agent memory that learns: long-term project memory with auto recall and retain, knowledge pages, deep reflection, and per-repo memory banks.
No one-line install — this plugin lives inside a larger repository and publishes no npm package.
agentscope-ai
Connects DeepSeek Harness to ReMe's local-first, self-evolving personal knowledge base: automatically captures completed main-agent conversations as user-owned Markdown memory, searches conversations and source material through reme_search with BM25, optional embeddings, and wikilink expansion, and schedules daily memory consolidation.
No one-line install — this plugin lives inside a larger repository and publishes no npm package.
agentscope-ai
Connects DeepSeek Harness to ReMe's local-first, self-evolving personal knowledge base: automatically captures completed main-agent conversations as user-owned Markdown memory, searches conversations and source material through reme_search with BM25, optional embeddings, and wikilink expansion, and schedules daily memory consolidation.
No one-line install — this plugin lives inside a larger repository and publishes no npm package.
zilliztech
Shared Markdown memory for DSH and other coding agents, with automatic capture, pre-step context injection, searchable recall, and memory-to-skill self-evolution through a review panel.
No one-line install — this plugin lives inside a larger repository and publishes no npm package.
vshulcz
Memory for coding agents — Claude Code, Codex, Cursor and 17 others. Indexes the sessions they already wrote to disk, including months from before you installed it, and recalls them in any of them. No LLM, no embeddings, one local Go binary.
Installed cleanly when we ran it
vshulcz
Reads the session files thirty-three other coding agents on this machine already wrote — Claude Code, Codex, Cursor, VS Code Copilot Chat, opencode, OpenClaw, Hermes, Kimi, Cline, Zed and more — including sessions from before it was installed: six tools (deja_recall, deja_session, deja_blame, deja_fix, deja_how, deja_remember), a /deja command, and optional automatic recall added to the runtime context. Local BM25 index, no LLM, no embeddings, no network (dsh plugin --profile web add dsh-deja).
Installed cleanly when we ran it