AGPL-3.0 self-evolving context database unifying agent memory, knowledge RAG and skills; connects to DeepSeek Harness via its generic MCP-client / Agent Plugins integrations, not a native dsh mode.
DSH integration
Ecosystem-related
Author-claimed
Safety audit
Unaudited
Last verified
2026-08-21
License
AGPL-3.0
01What can it help you accomplish?
Give an AI agent persistent memory, knowledge and skills in one browsable context database
Memories, resources and skills unified under the `viking://` protocol, browsable with ls/tree/find, L0/L1/L2 tiered on-demand loading, and observable retrieval trajectories
Developers building stateful AI agents who want deterministic, file-like access to agent memory instead of a black-box vector store
Wire long-term memory into a coding agent such as Claude Code, Codex, Cursor, MCP clients or LangChain
OpenViking recall injected into the agent's context and session memory auto-committed after each session
Coding-agent users who want cross-session memory and recall without manual note-taking
Run a ready-made AI agent on top of the context database
VikingBot agent started alongside the server via `openviking-server --with-bot`, chatted with via `ov chat`
Users who want an out-of-the-box agent built on OpenViking instead of integrating their own
02How to install into DeepSeek Harness
Prerequisites
- Python 3.10 or higher
- A model provider to configure during init — Volcengine, OpenAI, Codex OAuth, Kimi, GLM, or local Ollama
Installation steps
- 01
`pip install openviking --upgrade`
- 02
`openviking-server init` — interactive wizard: providers, models, writes `~/.openviking/ov.conf`
- 03
`openviking-server doctor` — validate setup
- 04
`openviking-server` — start the server (background: `nohup openviking-server > openviking.log 2>&1 &`)
Verify the integration
- Run `openviking-server doctor` — checks the config file, Python version, provider connectivity, and disk space without a running server
- With the server running, the bundled `ov` client CLI works, e.g. `ov status`
03DSH integration and capability boundaries
No DeepSeek Harness-specific integration is documented in the README; OpenViking runs as a standalone context/memory server that agents reach through its generic integrations (MCP clients, Agent Plugins 1.0)
viking:// virtual filesystem for all context
memories, resources (docs, repos, web pages) and skills→one `viking://` URI tree browsed deterministically via `ov ls` / `tree` / `find` / `grep`
L0/L1/L2 tiered on-demand loading
any entry written into OpenViking→L0 abstract (~100 tokens), L1 overview (~2k tokens), L2 details — loaded only as deep as the task requires, cutting token spend
every entry is processed into three tiers on write (asynchronous semantic processing)Sessions become long-term memory
committed agent sessions→user preferences and agent experience extracted into long-term memory
after a session commits, OpenViking asynchronously extracts memory in the backgroundAgent integrations & ov CLI
Claude Code, Codex, OpenClaw, Hermes, Cursor, TRAE, OpenCode, MCP clients, LangChain/LangGraph and more→OpenViking recall injected into the agent's context with auto-committed session memory
`openviking-server init` writes `~/.openviking/ov.conf`; integrations modify the target agent's configuration
04Who is it for? When not to use it?
Good for
- Developers building stateful AI agents who want deterministic, file-like access to agent memory instead of a black-box vector store
- Coding-agent users who want cross-session memory and recall without manual note-taking
- Users who want an out-of-the-box agent built on OpenViking instead of integrating their own
Not for
- The server requires Python 3.10 or higher, plus a configured model provider (Volcengine, OpenAI, Codex OAuth, Kimi, GLM, or local Ollama) before it can serve context.
- The README documents no DeepSeek Harness (dsh)-specific integration; DSH users must rely on the generic integration lanes it lists (MCP clients, Agent Plugins 1.0), so a working dsh hookup is not guaranteed by the README alone.
- The project self-describes as early-stage, and the OpenViking Helper desktop console is still in beta for macOS and Windows x64 only.
05Compatibility, maintenance and safety notes
- The server requires Python 3.10 or higher, plus a configured model provider (Volcengine, OpenAI, Codex OAuth, Kimi, GLM, or local Ollama) before it can serve context.
- The README documents no DeepSeek Harness (dsh)-specific integration; DSH users must rely on the generic integration lanes it lists (MCP clients, Agent Plugins 1.0), so a working dsh hookup is not guaranteed by the README alone.
- The project self-describes as early-stage, and the OpenViking Helper desktop console is still in beta for macOS and Windows x64 only.
AGPL-3.0 · actively maintained (latest release v0.4.15, 2026-08-18)
06Frequently asked questions
How do I connect OpenViking to DeepSeek Harness?
The README does not document a DeepSeek Harness-specific integration. OpenViking ships generic integration lanes — MCP clients and Agent Plugins 1.0, alongside guides for Claude Code, Codex, Cursor, TRAE and OpenCode — which are the documented ways to hook any agent, including dsh, into the server.
Is it a native dsh integration or MCP?
Neither native dsh support nor a dsh plugin is documented in the README. Among the listed integrations, MCP clients is the generic machine-to-machine lane; setup details live in the linked docs site, not in the README itself.
What do I need before installing?
Python 3.10 or higher, and a model provider to configure during `openviking-server init` — Volcengine, OpenAI, Codex OAuth, Kimi, GLM, or local Ollama (the wizard can detect and install Ollama for you).
Where does my data go?
The self-hosted server keeps context locally and writes config to `~/.openviking/ov.conf`; model calls go to whichever provider you configure (local Ollama stays fully local). A managed SaaS on Volcano Engine also exists as an optional hosted edition.
What are the main limitations?
The project says it is still in its early stages, the OpenViking Helper desktop console is beta for macOS and Windows x64 only, and production use is expected via a standalone HTTP service deployment.
07Related DSH workflows
archify
by tt-a1i
Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.
nocobase
by nocobase
NocoBase is an open-source AI + no-code platform for building business systems fast. Instead of generating everything from scratch, AI works on top of production-proven infrastructure and a WYSIWYG no-code interface, so you get both speed and reliability.
learn-harness-engineering
by walkinglabs
Harness engineering beginner tutorial, from 0 to 1
skill
by anbeime
The most complete and fastest-updating Skills store: 416 curated original skill packs (docs, content, coding, ML, automation workflows), plus auto-indexed thousands of GitHub skills sortable by category, date, and stars — all ready to install.
08Data and sources
Integrations inject OpenViking recall into your agent's context and auto-commit session memory:
- [MCP clients](https://docs.openviking.ai/en/agent-integrations/06-mcp-clients)
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-08-21. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.