- Início
- Plugins
- Ferramentas e funções
- argo (dsh-plugin)
argo (dsh-plugin)
taxueseek/argo/packages/dsh-plugin
Busca unificada com verificação de evidências para agentes: mais de 120 engines com roteamento multilíngue, domínios verticais e cartões de modalidade estruturados, 10 ferramentas MCP além de orquestração wide_research, e um loop fetch-verify que preenche retroativamente pontuações de evidência.
Instalar
dsh plugin --profile web add github:taxueseek/argoEste plugin está no subdiretório packages/dsh-plugin do repositório.
README
English · 中文 · 日本語 · 한국어 · Español
Quick Start · Why Argo · Routing Proof · How It Works · AI Search & Sub-skills · DSH Plugin · Docs
Part of the taxueseek skill series (search & deep research): plainspoken-writing 75★ (AI-tone removal) · session-digger 34★ (cross-environment session mining) · taxue-invest 30★ (investment analysis) · taxueskills 25★ (decision system) · taxue-creative-style 19★ (creative illustration styles) · ime-lexicon 15★ (IME lexicon toolkit).
DeepSeek Harness (DSH) plugin ecosystem: dsh-files 43★ (folder upload + document parsing) · plugin-fast-adapt 15★ (plugin upgrade adapter) · taxue-dsh-artisan 3★ (visual creation) · dsh-plugin-guard 2★ (pre-install audit).
Argo is an open-source metasearch, web-fetch, and evidence-verification engine that lives inside your AI agent. It routes queries across hundreds of sources in 18 languages (web, academic, finance, code, local files, and leading AI search engines), falls back to keyless & local engines when API keys are absent, and verifies facts from full page text instead of trusting search snippets.
Quick Start
Zero-config works out of the box (API keys are optional). Pick your client:
- Claude Code (MCP):
claude mcp add argo -- npx -y argo-search - Agent Skill (
skills.sh— Claude Code, Cursor, Codex, Antigravity):npx skills add taxueseek/argo # Or install all 3 standalone Skills (argo, argo-wide-research, local-seek): npx skills add taxueseek/argo --full-depth --all - Cursor / Windsurf / LibreChat (
mcpServersJSON):{ "mcpServers": { "argo": { "command": "npx", "args": ["-y", "argo-search"] } } } - Local CLI (recommended for long-term local use):
curl -fsSL https://raw.githubusercontent.com/taxueseek/argo/main/scripts/install.sh | bash # Windows (PowerShell): irm https://raw.githubusercontent.com/taxueseek/argo/main/scripts/install.ps1 | iex # or via npm: npm install -g argo-search - DeepSeek Harness (DSH) Plugin:
dsh plugin --profile web add argo-search
Verify installation, requirements & optional API keys
argo search "python asyncio error handling" --verify 2 --json --fields agent
argo search --list-engines
- Requires Python 3.9+ (
pip install pyyaml) and Node.js 18+ (fornpx). - Optional keys (
DEEPSEEK_API_KEY,ARGO_YUANBAO_API_KEY,ARGO_TAVILY_API_KEY,EXA_API_KEY,ARGO_METASO_API_KEY,ARGO_BOCHA_API_KEY) improve quality when present and are skipped automatically when missing. See docs/MCP_SETUP.md and docs/ENGINE_CATALOG.md.
Why Argo
| Capability | Built-in Web Search | Commercial Search APIs (Tavily / Exa / Serper) | Argo |
|---|---|---|---|
| Pricing & Keys | Tied to host quota | Paid per call; API key required | Free & keyless fallback (optional keys boost quality) |
| AI Search Aggregation | Single host backend | Single vendor index | Unifies keyless (tavily_free, parallel_free, anysearch) + BYOK (DeepSeek Search, Tencent Yuanbao/Hunyuan, Metaso, Bocha, Tavily, Exa) |
| Source Routing | Single generic index | Generic web index | Domain + 18-language routing across academic, finance, code, news & local files |
| Fact Verification | Snippet only | Snippet or raw chunks | Built-in --verify & --numverify (fetches source & scores credibility) |
| Context Efficiency | Verbose HTML/JSON | Raw chunks | Agent-compact output (--fields agent ~4.3 KB) |
Query-Shaped Routing
Argo classifies each query by domain and language before dispatching, hitting first-party sources directly and triggering early-stop once consensus is reached:
- Academic →
arxiv,semantic_scholar,openalex,crossref,pubmed(--academic-deep) - Finance & Macro →
sec_edgar,yahoo_finance,sina_quote,eastmoney - Code & Tech →
stackoverflow,github,octen,context7 - AI Search →
tavily_free,parallel_free,anysearch,deepseek_search,yuanbao,metaso,bocha,exa,tavily,you - Deep Research →
python3 scripts/research.py "topic" --depth deep --jsonoutputs a structured dossier (sources, coverage gaps, quality gates)
How It Works
Evidence Scoring (Selection × Absorption)
Search engines optimize for clicks; agents need verifiable facts. Argo scores every candidate along two orthogonal axes:
- Selection: domain authority, consensus across engines (
RRF), freshness, and SERP-shell rejection (blocksbaidu/sandsogou/linkredirect stubs from posing as primary sources). - Absorption: actual readable density after fetching the full page (
--verify N) and numerical cross-checking (--numverify Nfor prices, financials, and dates).
Budget Modes (--mode)
| Mode | Behavior | Best for |
|---|---|---|
fast | Free + local local_* engines only, zero API spend | High-frequency agent lookups |
auto | Cost-aware default: free first, escalates to keyed sources when needed | Daily coding & general research |
deep | Broad multi-source fan-out, disables early-stop, pairs with --verify | High-stakes finance, legal, academic dossiers |
budget | Strict daily/monthly quota caps with local fallback | Unattended batch & cron workflows |
AI Search & Sub-skills
Skills & Internal Modules
Argo exposes 3 orthogonal Skills (argo, argo-wide-research, local-seek) and bundles 3 internal pipelines under sub-skills/ driven via CLI flags or fallbacks:
| Module | Type | Capability |
|---|---|---|
| argo-wide-research | Standalone Skill | Multi-track parallel deep research & forensics orchestration with citation ledger and quality gates |
| local-seek | Standalone Skill | Hybrid BM25F rerank + FTS5 + fzf search for local notes, markdown, and code (argo seek) |
| local-search | Internal Pipeline | 30 zero-cost local aggregation engines (--local-first) |
| ego-search | Subcommand (argo ego-search) | Real-browser logged-in search for Zhihu, Xiaohongshu, WeChat Official Accounts (off by default) |
| js-run | Internal Pipeline | Sub-millisecond headless JS execution for environment probes and pure-compute pages |
19 MCP Tools
argo_search, argo_local_search, argo_local_read, argo_recompute, argo_research, argo_evidence, argo_clarify, argo_fetch, argo_crawl, argo_screenshot, argo_pdf, argo_social_search, argo_article, argo_job, argo_extract, argo_preflight, argo_answer, argo_watch, argo_cite.
DSH Plugin
Argo ships a first-class DeepSeek Harness (DSH) plugin (@taxueseek/argo-dsh) with three invocation channels from one capability set:
- 19
mcp__argo__*tools (full MCP bundle; default MCP surface exposes 4 core tools, setARGO_MCP_TOOLS=allfor all 19). - Search +
wide_researchparallel orchestration (subpackage). - Host
web_search/web_fetchseam replacement (requires explicit provider pin in the web profile; see packages/dsh-plugin/README.md).
The built-in Argo Workbench provides a browser UI with 5 modes (Web Search, Hot Topics, Deep Research, Local Search, Scheduled Search), adaptive home suggestions, and a side-by-side verified evidence panel; the settings UI exposes 18 native first-class tools, 35 behaviour switches, and shares DSH's native DEEPSEEK_API_KEY credential store with zero plaintext echoing:
![]() Argo Workbench — Home: 5 search modes, adaptive suggestions & specialized theme cards |
![]() Argo Workbench — Evidence View: structured synthesis + verified source & line-level citations |
![]() Settings — Tools (18 native tools) |
![]() Settings — Engines (35 switches & quotas) |
![]() Settings — Keys (shared DSH store) |
Docs & Changelog
- docs/ENGINE_CATALOG.md · docs/MCP_SETUP.md · docs/ARGO_INTRO.md · docs/为什么选择argo.md · docs/CHANGELOG.md
| Version | Highlights |
|---|---|
| v2.16.0 | DSH Argo Workbench UI, direct 4-stage CLI verification, linux.do + Keenable free channel (312 sources), Jina keyless fallback, concurrency & cache hardening |
| v2.15.0 | Zhihu full chain, evidence-layer authority passthrough, keyless 3-tier semantic fallback, MCP generic connector (type: mcp), route zero-based domain scoring, 311 sources |
| v2.14.1 | Architecture slimming, MCP 3+1 orthogonal tools + backward-compat aliases, 304 sources, fail-closed secret_guard.py redaction |
| v2.14.0 | Parser layer consolidation, 300 sources, badcase ledger loop |
| v2.13.0 | Documentation consolidation, 22-state-machine SSOT, dispatch tail grace |
v2.16.0 Release Summary & Capability Snapshot
Capabilities (v2.16.0)
v2.16.0 introduces the browser-based Argo Workbench in the DSH plugin (5 modes, adaptive home suggestions, theme cards, and side-by-side verified citations) backed by a direct bin/argo CLI 4-stage verification pipeline and local-seek integration; adds the linux.do community source (311→312 sources) and activates the keenable free channel (100k/mo); refactors Jina Reader to keyed-with-keyless-fallback; and hardens circuit-breaker, quota, cache-slot, and routing-latency behaviour.
v2.16.0: Argo Workbench UI + Direct 4-Stage Pipeline + Sources & Concurrency Hardening
See docs/RELEASE_NOTES_v2.16.0.md and docs/CHANGELOG.md.
v2.15.0: Zhihu Full Chain + Evidence Authority Passthrough + MCP Connector
See docs/RELEASE_NOTES_v2.15.0.md and docs/CHANGELOG.md.
v2.14.1: Architecture Slimming + MCP 3+1 Tools + Security Redaction
Good search is not about seeing more—it is about concluding with confidence, and knowing when you still should not.
If Argo has ever helped you reach a more confident conclusion, give it a Star to help more people find it.
Contributing & License
Issues and PRs are welcome (see docs/ADDING_NEW_ENGINE.md to add a source). Licensed under Apache-2.0.
Plugins relacionados
archify (deepseek-harness)
tt-a1i/archify
WeKnora (dsh-weknora)
tencent/weknora
next-ai-draw-io (dsh-plugin)
dayuanjiang/next-ai-draw-io
weknora
tencent/weknora




