WeKnora
Tencent
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
PROJECT TOPICS
INSTALL REFERENCE
dsh plugin --profile web add github:BharathBillawa/dsh-tool-ddgs
该命令指向仓库当前默认分支;尚无绑定当前 commit 的完整验证结果。
PROJECT README
DuckDuckGo web search and URL fetch tools for DeepSeek Harness.
Zero required system dependencies — search is pure Node.js, fetch uses @mozilla/readability with optional trafilatura fallback for higher quality extraction.
dsh plugin --profile web add github:BharathBillawa/dsh-tool-ddgs
Then restart dsh. The bundle patch automatically:
web_search (DuckDuckGo Lite, pure Node)web_fetch (content extraction, saves to file)pip install trafilatura for better content extractionweb_searchSearch the web using DuckDuckGo Lite. Pure Node.js — no Python, no subprocess, no API key.
ctx.web providerweb_fetchFetch a URL and extract readable text content:
trafilatura (if available) or @mozilla/readability/tmp/dsh-web-fetch/<url-slug>.mdIf the preview answers the question, the model responds immediately. If more detail is needed, the model uses dsh's built-in read tool with offset/limit to read specific sections from the saved file — just like reading any local file.
This avoids dumping 100K+ chars into context for a simple question about one section of a long article.
fetch() → @mozilla/readability (DOM extraction via linkedom). Falls back to trafilatura via Python subprocess when available (better quality on complex pages)./tmp/dsh-web-fetch/<url-slug>.mdThe plugin registers both:
ctx.web search provider (id: "ddgs") — powers the native Search action in the agent loopweb_search and web_fetch tools — directly callable by the modelThe bundle patch configures itself. No manual cordis.patch.yml editing needed.
MIT
CLASSIFICATION EVIDENCE
系统优先读取 GitHub Topics,再与站内分类词典和词根规则比对。当前命中: web-search、websearch。