🚚 Project update · 项目进展 — The standalone small-team product now lives at Staffwright: same engine, complete product packaging, international-first. This repository continues as the deepDDW DSH-plugin line (memory & knowledge base for DeepSeek Harness).

独立的小团队产品线已迁移至 Staffwright（同一引擎、完整产品化、面向国际市场）。本仓库继续作为 deepDDW 的 DSH 插件线（DeepSeek Harness 的记忆与知识库）维护。

deepDDW — Memory & Knowledge Base for DeepSeek Harness, Reachable from Any Device on Your LAN

English · 简体中文

deepDDW gives DeepSeek Harness (DSH) the three pieces it's missing — memory, a knowledge base, and document search — and makes all of it reachable from any device on your LAN. No app install. No DSH source changes.

🧠 Memory — cross-session long-term memory, write/search via DSH's official MCP interface
📚 Knowledge base — ingest & search your docs (industry docs, SOPs, research notes) anytime
🎒 Take your AI assets with you — one click packs memory + knowledge into a portable ddw_assets_v1.zip (importable into DDW AI Hub or another deepDDW). Your data, your call — no lock-in
🌐 LAN-wide multi-device — deploy once; phones, laptops and tablets on the same network all use the same DSH workbench

Try it in 60 seconds:

npm i -g @deepseek-ai/dsh              # 1. install official DSH on the server
git clone https://github.com/ccch713/deepddw.git && cd deepddw
./install.sh --with-dsh                # 2. install deepDDW
./install.sh --port 8600               # 3. start
# 4. from any device on your LAN: open http://<server-ip>:8600/  (phone: scan the QR to auto-pair)

📸 Screenshot: phone / tablet accessing the workbench (coming soon).

Status: v0.8.1 · MIT · CI (pytest + ruff) ✅ · DSH for Teams — multi-user, LAN multi-device, memory & KB with team distillation · migration import/export, scope promote, incognito, retrieval health · org binding server (bindcode-v1, optional) · virtual office (view-only activity visualization) · AI assets export/import (ddw_assets_v1, anti-lock-in) · Listed in awesome-deepseek-harness · Roadmap below

⚠️ IMPORTANT — Read Before Installing

deepDDW implements its own memory and knowledge-base isolation. To avoid conflicts or memory confusion, before installing:

Back up your existing memory and knowledge-base contents (wherever they live in your DSH setup);

Uninstall/disable any other memory or knowledge-base plugins you have installed;

Only then install deepDDW and let it own the memory & knowledge-base stack.

Running deepDDW alongside other memory/KB plugins may cause data conflicts or memory mixing between namespaces. You have been warned. ⚠️

Why deepDDW?

Most DSH extensions give you memory alone. deepDDW is a complete workstation — memory + knowledge base + document search + LAN-wide multi-device access:

Official DSH limitation	deepDDW solution
🔒 Local-only access	✅ LAN-wide access: deploy once on a server; desktops, laptops, phones and tablets on the same network all connect
🧠 No memory	✅ Long-term memory write/search — conversation experience is accumulated
📚 No knowledge base	✅ Knowledge base search/ingest — industry docs, SOPs, research notes, callable anytime

In one sentence: turn a "personal toy" into a tool a small team can actually use — fully packaged, easy to deploy, low maintenance, ready for small businesses (up to ~20 people) for their daily AI workflow.

deepDDW distills lessons from real-world enterprise deployments into the DSH ecosystem as open source (MIT).

Which Scenario Fits You?

deepDDW is built for individuals, families, departments and small businesses — roughly up to 20 people and 20 devices on one LAN. Find your scenario:

Scenario	Typical setup	What you get
🧑‍💻 Individual · multi-device	One person; laptop + phone + tablet	Deploy once on any always-on machine you own (NAS / mini host / old PC): every device of yours shares the same memory & knowledge base, and the data never leaves your hardware. Don't want to run anything? Pro Cloud hosts it for you with managed multi-device sync and daily backups.
👨‍👩‍👧 Family · multi-person, multi-device	A household; one server, several members	"Deploy once, the whole family can use it." Each member gets an independent account with a private memory namespace; family distillation merges everyone's recent highlights into a shared family space (rule-based dedup — works even without an LLM key).
🏢 Department-level	One department (≤20 people) inside a larger organization	Run deepDDW as your department workbench. Optionally enable the bindcode-v1 org backend: staff apps bind with a scan code, the server becomes the org backend for the assistant — while each member keeps personal mode (their own models, on-device memory) and can switch back at any time, unbinding deletes nothing.
🏪 Small business	A company of up to ~20 people running daily AI workflows	Team mode: multi-user accounts, team distillation (LLM-refined, deduplicated shared team memory), scope promote, incognito sessions, retrieval health — all in the open-source build. Need SSO, audit logs or private-deployment support on top? That's the Enterprise tier (see Commercial & Support).

Rule of thumb: one instance per team of ≤20 people on one network — if your scenario fits in one room, one floor, or one VPN, deepDDW fits you.

How It Works (Technical Path)

📱 Phone / 💻 Desktop / 📱 Tablet / 🖥️ Laptop — any device on the LAN
   │                  (browser access, no App install)
   ▼
deepDDW Gateway (one server on the LAN)
   ├─ /dsh/*   proxy → DSH engine (official UI, model config & chat untouched)
   ├─ /api/*   proxy → DSH RPC/API
   └─ /api/v1/*  deepDDW capabilities: Knowledge Base / Memory / Docs / LLM config
        │
        │  DSH official MCP client (streamable-http)
        ▼
deepDDW MCP tools (auto-invoked by the model)
   ├─ mcp__deepddw__ddw_kb_search          knowledge base search
   ├─ mcp__deepddw__ddw_memory_put         write memory
   ├─ mcp__deepddw__ddw_memory_search      search memory
   └─ mcp__deepddw__ddw_docs_portal_search document search

Integration = DSH standard MCP: DSH natively supports MCP clients; deepDDW exposes a standard streamable-http endpoint — zero intrusion, zero changes to DSH source. The UI, settings and model configuration all remain official.

Virtual Office (0.8.0)

Open /ui/office.html and watch your deepDDW at work: every subsystem is a pixel-art staff member — the gateway doorman waves devices in, the chat receptionist types away, the memory butler files notes, the librarian shelves new docs, the meter clerk bills LLM calls. Real activity drives the animations (no fake loops: 30 min without events → back to idle), failures raise a banner, and the day's digest is importance-weighted. Fully programmatic rendering — zero third-party art assets, zero runtime dependencies. View-only by design: the API exposes nothing but job titles and whitelisted count phrases — never document contents, memory values, or chat transcripts.

Why Does It Work on Your LAN?

The official DSH listens on localhost only (for security), so phones/tablets cannot connect. deepDDW solves this with gateway proxying:

DSH stays bound to localhost (official security design preserved)
deepDDW gateway listens on the LAN, any device opens http://<server-ip>:8600/ to reach the original DSH workbench
All data stays on your server — never leaves the LAN

Deploy once, the whole family/team can use it — a capability the official DSH does not provide.

Quick Start

# 1. Install DSH (official) on the server
npm i -g @deepseek-ai/dsh

# 2. Install deepDDW (packaged, one command)
git clone https://github.com/ccch713/deepddw.git
cd deepddw && ./install.sh --with-dsh

# 3. Start
./install.sh --port 8600

# 4. Open from any device on the LAN:
#    http://<server-ip>:8600/   → original DSH workbench
#    Phones/tablets: "Add to Home Screen" for an App-like experience

# 5. Add your API Key in DSH Settings → Models
# 6. In chat, ask the model to "search the knowledge base" or "remember ..."
#    → it auto-invokes the mcp__deepddw__* tools

Requirements: one ordinary computer/server (8 GB RAM minimum, 16 GB+ recommended), Python 3.11+, no GPU needed (LLM via cloud API or local Ollama).

Windows (standalone exe)

A Windows build is produced automatically by the windows-build workflow — download deepddw-windows.zip from the latest Actions → Artifacts:

# 1. Unzip anywhere (no Python/Node needed on the target machine)
deepddw-windows/deepddw.exe

# 2. Optional: point data/config at a custom location
set DDW_DATA_DIR=%USERPROFILE%\.deepddw
set DDW_ACCESS_TOKEN=<your-token>

# 3. Start (listens on 0.0.0.0:8500) → open http://<host>:8500/health
deepddw.exe

Upgrades are cheap: replace the whole folder with a newer zip — your data (under %USERPROFILE%\.deepddw) is untouched. See docs/windows-packaging.md for the full evaluation (PyInstaller one-dir + CI auto-build) and the manual build steps.

Multi-Device on LAN (0.2.0)

deepDDW is built for up to 20 devices on your LAN sharing one gateway:

Device identity — each browser persists a device_id (localStorage) and can set a friendly name on the launcher; reconnects keep the same identity.
Online status — devices register/heartbeat to the gateway; /api/v1/status (Token-protected) shows who is online, active WebSockets, request counts, DB size and version. The launcher renders a live status card for admins.
Rate limiting — sliding-window per Token + per IP (default 60 req/min/token, global cap → 503 overload protection); configurable via config/deployment.yaml → security.rate_limit.* or DDW_RATE_LIMIT_* env.
SQLite concurrency — WAL + busy_timeout=5000 + synchronous=NORMAL on every connection, plus a process-wide write lock for cross-table transactions (20 concurrent writers verified, no database is locked).

POST /api/v1/device/register    # register / rename this device (idempotent)
POST /api/v1/device/heartbeat   # keep-alive
GET  /api/v1/status             # status panel (token required)

Also in 0.2.0:

Workspace isolation — devices pick a workspace (default shared); memory/logs and MCP memory tools are scoped per workspace, docs filtered by slug prefix. Legacy clients are unaffected.
Session resume across devices — recent session summaries (up to 5) with a "continue" button: pick up a conversation on your phone where you left off on desktop.
One-click backup / restore — backup via API (downloadable); restore validates the SQLite file (header + integrity check) and keeps a .pre-restore safety copy before replacing the main DB.
Optional TLS — one-command self-signed cert (scripts/gen_self_signed_cert.sh, 1-year), enabled via security.tls.*; HTTP unchanged when off. For external access prefer a Caddy/Nginx reverse proxy (see docs/tls.md).
Version / upgrade check — /api/v1/version reports latest_version / update_available (GitHub releases, 1h cache, offline-degraded); the launcher shows an upgrade banner.

Security & Privacy

Capability	Description
🔐 Local-only data	Knowledge base & memory stay on your server, never leave the LAN
🏠 LAN password-free	Optional (opt-in): LAN requests skip the token — OFF by default (set `DDW_LAN_BYPASS=1` to enable; trusted LANs only)
🌐 External access	Optional Token gate (short-code supported); unauthorized → 401
🛡️ DSH secure binding	DSH stays on localhost; gateway exposes it — official security design preserved

Tech Stack & License

Component	Description	License
DSH engine	Official DeepSeek Harness (source untouched)	MIT
deepDDW gateway	FastAPI + SQLite + MCP dual-protocol	MIT
Memory / Knowledge base	SQLite storage (agentmemory / vectors optional)	MIT
Search	Optional SearXNG	AGPL-3.0 (server-side HTTP, exemption assessed)

deepDDW itself: MIT License — free to use, modify, and commercially deploy; keep the copyright notice.

See NOTICE for full third-party attribution.

Ecosystem & Feedback

Extend with official DSH plugins: deepDDW keeps DSH's native plugin mechanism intact. Install official plugins straight from the npm registry via the DSH official command — the only channel we recommend, to avoid supply-chain poisoning:
```
dsh plugin --profile web add <npm-package>   # official npm registry only
```
See SECURITY.md for our third-party plugin disclaimer and what deepDDW guarantees (memory & knowledge base only; no data theft/exploitation/sale).
Knowledge distillation: use whatever distillation skill / workflow you prefer — the methodology is yours; deepDDW provides the complete pipeline "distilled output → searchable knowledge base → model-usable". More plugins and tools are on the way.
Memory / knowledge migration: knowledge base uses standard SQLite; memory is organized by namespace/key/value — import from other agents or tools.
Feedback: we'd love to hear how you use it; stronger open-source tools are coming in future releases.

Enterprise Backend for the DDW AI Assistant

deepDDW ships an optional, off-by-default plugin that lets a single instance act as the organization backend for the DDW AI Assistant app family, via the open bindcode-v1 protocol. The admin issues a short-lived bind code; staff paste or scan it in the app (Settings → Advanced → Connect to enterprise server); from then on those members can run their assistant on your infrastructure.

Three things worth knowing before you enable it:

The LLM provider is yours. Bound members chat through this instance's llm_gateway — whatever provider you configured (DeepSeek, Ollama, or any self-hosted OpenAI-compatible gateway). Nothing in the plugin points to any hosted service, and there is no preset channel.
Binding is an identity relation, not lock-in. Members can switch back to personal mode (their own models, their on-device memory) at any time; unbinding changes nothing on their device (protocol §4). The server never holds staff personal data, and unbind deletes nothing.
Blast radius is small. A member-level access_token only unlocks the plugin's chat endpoint — never the admin API. Bind codes are HMAC-signed, short-lived, use-capped and revocable; the public endpoints are rate-limited (10 req/min per product token).

Quick start:

# 1) enable in config/deployment.yaml (org_relay.enabled: true + product_tokens), then:
curl -X POST :8500/api/v1/plugins/ddw-org-relay/admin/orgs      -H "Authorization: Bearer $DDW_ACCESS_TOKEN"      -H 'Content-Type: application/json' -d '{"name":"Acme Clinic"}'
curl -X POST :8500/api/v1/plugins/ddw-org-relay/admin/orgs/<org_id>/bindcode      -H "Authorization: Bearer $DDW_ACCESS_TOKEN"      -H 'Content-Type: application/json' -d '{"ttl_min":15,"max_uses":50}'
# 2) staff app: Settings → Advanced → Connect to enterprise server → paste code

Full endpoint list, config reference and security notes: plugins/ddw_org_relay/README_EN.md.

Commercial & Support

deepDDW is free and fully featured forever. The paid tiers exist for exactly two things: convenience (hosting, zero-ops) and enterprise collaboration (permissions, audit, compliance). Every core capability ships in the open-source build — there are no feature gates and no "Pro-only" paywalls, period.

Tier	Price	Best for	What you get
Open Source	Free forever	Individual developers, self-hosters	MIT licensed, full features, no feature gates
Pro Cloud	¥19/mo or ¥199/yr	People who'd rather not run it	Cloud-hosted memory & knowledge base, zero ops, managed multi-device sync, daily backups
Founder License (lifetime)	¥499, one-time	Early supporters	Lifetime Pro. Capped at the first 100 licenses — once they're gone, they're gone
Enterprise	From ¥9,800/yr	Teams and companies	Multi-user & permissions, SSO, audit logs, private-deployment support (remote), commercial license letter, 24h priority response

Enterprise on-site deployment & implementation: ¥3,000 per engagement.
VAT invoices available for corporate purchases.
Sales & support: GitHub Issues.

Pro Cloud — skip the ops

Everything you'd get from self-hosting, running in the cloud: hosted memory and knowledge base, managed multi-device sync, automatic daily backups. ¥19/month, or ¥199/year (works out to about ¥16.6/mo). Built for people who want the full deepDDW experience without owning a server.

Founder License — lifetime, 100 seats only

Pay ¥499 once, keep Pro for life. A permanent thank-you to early supporters — 100 seats, first come first served, never restocked. When the last seat sells, this tier is retired for good. No second wave.

Enterprise — built for teams

User management and permissions, SSO, audit logs, remote private-deployment support, and a formal commercial license letter — the document your procurement and legal teams actually need. 24-hour priority response included. On-site deployment and implementation available at ¥3,000 per engagement.

Don't need any of the paid tiers? Totally fine — deepDDW stays free either way. Star the repo — it means a lot.

Roadmap

Only items actually planned or already delivered are listed here.

Delivered:

deepDDW — enterprise-grade capability, open-sourced for everyone.

deepddw (ddw-teams-panel)

安装

README

deepDDW — Memory & Knowledge Base for DeepSeek Harness, Reachable from Any Device on Your LAN

⚠️ IMPORTANT — Read Before Installing

Why deepDDW?

Which Scenario Fits You?

How It Works (Technical Path)

Virtual Office (0.8.0)

Why Does It Work on Your LAN?

Quick Start

Windows (standalone exe)

Multi-Device on LAN (0.2.0)

Security & Privacy

Tech Stack & License

Ecosystem & Feedback

Enterprise Backend for the DDW AI Assistant

Commercial & Support

Pro Cloud — skip the ops

Founder License — lifetime, 100 seats only

Enterprise — built for teams

Roadmap

相关插件

hindsight (coding-agents)

OpenViking (dsh-memory-plugin)

MemOS (memos-local-plugin)

ReMe (dsh)

安装

README

deepDDW — Memory & Knowledge Base for DeepSeek Harness, Reachable from Any Device on Your LAN

⚠️ IMPORTANT — Read Before Installing

Why deepDDW?

Which Scenario Fits You?

How It Works (Technical Path)

Virtual Office (0.8.0)

Why Does It Work on Your LAN?

Quick Start

Windows (standalone exe)

Multi-Device on LAN (0.2.0)

Security & Privacy

Tech Stack & License

Ecosystem & Feedback

Enterprise Backend for the DDW AI Assistant

Commercial & Support

Pro Cloud — skip the ops

Founder License — lifetime, 100 seats only

Enterprise — built for teams

Sponsor — buy the author a coffee

Roadmap

相关插件

hindsight (coding-agents)

OpenViking (dsh-memory-plugin)

MemOS (memos-local-plugin)

ReMe (dsh)