61 lines
2.9 KiB
Markdown
61 lines
2.9 KiB
Markdown
# DeepSeek Harness (dsh) — plugin shortlist
|
|
|
|
Pulled 2026-08-25 from https://github.com/topics/dsh-plugin (the topic feed is
|
|
noisy, so this is the curated subset relevant to the family home lab).
|
|
|
|
**Start here:** `awesome-dsh-plugin/awesome-dsh-plugin` — the curated index of
|
|
dsh plugins (categorized, maintained). Everything below is notable from the
|
|
topic feed itself.
|
|
|
|
## Knowledge / Docs / Summarize (matches "Docs, Links — summarize" todo)
|
|
- **Tencent/WeKnora** — open-source knowledge platform: turns raw documents
|
|
into a queryable RAG layer. Good fit for family docs/wiki summarisation.
|
|
- **volcengine/OpenViking** — self-evolving context/memory DB for agents
|
|
(unify memory + knowledge).
|
|
- **distilly** — distill "how they think" into reusable skills for any agent
|
|
(good for teaching the kids' assistants skills).
|
|
- **nocobase/nocobase** — AI + no-code platform (if we want a plugin that
|
|
builds data apps).
|
|
|
|
## Image / Media (matches "Image ingest/create" todo)
|
|
- **liustack/modlens** — vision plugin: lets dsh "see" images (ingest/understand).
|
|
- **freestylefly/awesome-gpt-image-2** — industrial prompt engine + 530+
|
|
reverse-engineered templates for image generation.
|
|
- **Nagi-ovo/voyager** — enhancement suite (Gemini/AI Studio/Claude/ChatGPT,
|
|
multimodal).
|
|
- **nexu-io/open-design** — design plugin (open-source alternative to Claude
|
|
Design; good for Sam's portfolio work).
|
|
|
|
## Memory
|
|
- **EverMind-AI/EverOS** — portable, local-first, Markdown-native memory layer
|
|
for agents.
|
|
- **MemTensor/MemOS** — ultra-persistent memory OS for LLM agents.
|
|
- **agentscope-ai/ReMe** — "Remember Me, Refine Me" memory management kit.
|
|
|
|
## UI / Desktop
|
|
- **anywhere-labs/dsh-desktop** — modern desktop client for the dsh plugin
|
|
ecosystem ("everything is a plugin, the desktop is a plugin").
|
|
- **zhu1090093659/dsh-web** — dsh Web plugin aggregator pack.
|
|
- **crafter-station/petdex** — public gallery of animated pets for agents
|
|
(fun for the kids' instances).
|
|
|
|
## Dev / Agent tooling (power users / Sam)
|
|
- **esengine/DeepSeek-Reasonix** — DeepSeek-native coding agent for the
|
|
terminal.
|
|
- **ruvnet/ruflo** — original agent "meta-harness" (multi-player swarms —
|
|
advanced).
|
|
- **tt-a1i/archify** — agent skill for architecture/workflow/sequence
|
|
diagrams.
|
|
- **yjh051108/dsh-routing-suite** — injector + router-standard kit for dsh.
|
|
- **xiaobright/dsh-anchored-standard** — two-phase dsh preset bootstrap.
|
|
|
|
## Notes
|
|
- Topic feed total is ~11k repos; most are non-dsh / gamed. Use the
|
|
awesome-dsh-plugin index before installing anything.
|
|
- Our own dsh is a lightweight FastAPI+SSE chat; plugins from the ecosystem
|
|
target the official DeepSeek Harness client — wiring them in means either
|
|
adopting the official harness or adapting individual ideas into our app.
|
|
- todo.txt already tracks: "DeepSeek Plugins: Docs/Links summarize" and
|
|
"Image ingest/create" — pick candidates from Knowledge/Docs and Image/Media
|
|
above.
|