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
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:volcengine/OpenViking#path:/examples/dsh-memory-plugin
Any plugin you install runs third-party code with your own permissions — it can read your files, use your credentials, and reach the network, and tool approvals don’t sandbox it. GitHub-sourced plugins also run build scripts at install time. Only install sources you trust, and pin a commit (github:owner/repo#sha).
README
An installable DeepSeek Harness bundle that adds OpenViking auto-recall, session capture, viking:// URI protection, and model-invocable memory tools.
Requirements
@deepseek-ai/dsh0.1.0-rc.6- Node.js
^22.19.0or>=24 - A reachable OpenViking server
The bundle has no runtime npm dependencies. Its tool and message structures
come from the DSH constructors (defineTool from @deepseek-ai/dsh-tools,
createUserMessage from @deepseek-ai/dsh-llm) behind exact-pinned
peerDependencies that DSH exposes through its profile fallback at boot time, so
the definitions track DSH's contracts instead of hand-built object shapes.
It is tested against 0.1.0-rc.6; install that exact DSH release because
prerelease package dist-tags are not synchronized across the package family.
Why injection uses pre-step user messages, not the system prompt
Recall and profile context enter through the agent/pre-step waterfall as
durable, source-attributed user messages (source: { kind: 'plugin', … }).
They are deliberately not added to the system prompt: a DSH preset whose
persona declares complete: true (the stock minimal preset does) restores
that persona as the sole prompt section after assembly, silently discarding
every other contribution — a system-prompt-based memory plugin loses its
context under such presets with no error. Pre-step injection also makes each
injection a session event that replays, is visible to compaction, and never
reaches request/header.
Install
From the OpenViking repository:
dsh plugin --profile default add ./examples/dsh-memory-plugin
Or install the published package:
dsh plugin --profile default add @openviking/dsh-memory-plugin
Confirm that the profile includes the bundle:
dsh --profile default --dump-config
The package patch mounts the runtime inside a Cordis group with an isolated openvikingMemory service.
Configuration
OpenViking credentials use the same resolution order as the other memory plugins:
OPENVIKING_*environment variables~/.openviking/ovcli.conf~/.openviking/ov.conf
Common environment variables:
| Variable | Purpose |
|---|---|
OPENVIKING_URL / OPENVIKING_BASE_URL |
OpenViking server endpoint |
OPENVIKING_API_KEY / OPENVIKING_BEARER_TOKEN |
Bearer credential |
OPENVIKING_ACCOUNT |
Trusted-mode account |
OPENVIKING_USER |
Trusted-mode user |
OPENVIKING_PEER_ID |
Explicit actor peer |
OPENVIKING_WORKSPACE_PEER |
Derive a peer from each DSH session workspace by default |
OPENVIKING_RECALL_PEER_SCOPE |
all for cross-workspace recall or actor for isolation |
The patch can also carry plugin config:
- insert:
- id: openviking-memory
name: '@deepseek-ai/cordis-plugin-group'
group: true
isolate:
openvikingMemory: true
config:
- id: openviking-memory-runtime
name: '@openviking/dsh-memory-plugin'
config:
endpoint: http://127.0.0.1:1933
recallTokenBudget: 2000
scoreThreshold: 0.35
captureToolResults: false
commitTokenThreshold: 20000
Behavior
agent/session-startinjects the OpenViking profile and available-memory index throughagent.inject().agent/pre-stepretrieves with the current step input and appends a durable plugin message to that same step.session/eventcaptures user, assistant, and optionally tool-result messages without scraping a transcript.turn/endchecks the OpenViking pending-token threshold and commits when required.- Failed writes enter the shared OpenViking pending queue for replay at the next session start.
tools/pre-executeblocks DSH filesystem and shell tools from treatingviking://URIs as local paths.
Each DSH session maps to dsh-<session-id> in OpenViking. Workspace-derived actor peers are resolved per session and sent on every session-specific request.
Tools
The bundle registers:
viking_searchviking_readviking_browseviking_rememberviking_forgetviking_add_resourceviking_archive_expand
viking_forget performs permanent deletion. The calling model should use it only when the user explicitly requests deletion.
Testing
npm ci # installs the exact-pinned dsh devDependencies the tests exercise
npm test # node --test *.test.mjs — runs in the repo's PR workflow
live-recall.test.mjs is an opt-in end-to-end gate against a real OpenViking
server: it stores a sentinel memory through a session commit, waits for
extraction, and asserts recall returns that sentinel — the property no stub
can certify. Enable it with OPENVIKING_E2E=1 plus the normal credential
chain; it skips otherwise (including in CI until a server secret exists).
Links
More in this category
vectorize-io/hindsight#coding-agents★ 20019
Hindsight, agent memory that learns: long-term project memory with auto recall and retain, knowledge pages, deep reflection, and per-repo memory banks.
dsh-engramory★ 154
The Engramory curated-memory discipline as an installable plugin ([npm: dsh-engramory](https://www.npmjs.com/package/dsh-engramory)): a deterministic 200-line / 25 KB cap on the `MEMORY.md` index via `ctx.tools.guard()` — growth denied, a shrinking rewrite always passes — plus the protocol registered as a runtime skill. The store is plain markdown, one file per fact, shared with Claude Code, Codex, Kiro, and OpenClaw.
omdsh-dev/dsh-mnemon★ 40
Cross-agent, local-first persistent memory plugin for DeepSeek Harness (DSH), powered by Mnemon. It shares long-term memory across Mnemon-enabled agents and adds runtime memory, searchable project documents, semantic recall, knowledge graph, and a Sidebar UI.
LoserFox/distill★ 19
Automatic conversation distillation: background subagent reflection + skill create/update.
Tyan66666/billion-context-dsh★ 16
Model-driven context compression (Active Context Pruning) for DeepSeek Harness: the model decides when and what to compress.
Aik358/dsh-auto-memory★ 15
Auto-memory for DSH: three-layer memory (user / project notes / daily logs) with automatic injection, per-turn auto-consolidation, AI greetings, smart search, a calendar view and a settings page, plus inheritance of other AI tools' memories.