Argus

Multi-provider web search broker for AI agents. Routes across SearXNG, DuckDuckGo, GitHub, Brave, Tavily, Exa, and more — using RRF fusion, content extraction, and budget-aware routing so you don't waste your free search credits.

Features at a glance:

• Multi-provider search — 11 providers, one API, free-first tier routing
• 5,000+ free queries/month — automatic budget tracking, exhausted providers skipped
• Content extraction — 9-step fallback chain with quality gates (local + external)
• Multi-turn sessions — pass session_id for conversational search refinement
• 4 search modes — discovery, research, recovery, grounding
• Dead URL recovery — first-class /recover-url endpoint with archive fallbacks
• 4 integration paths — HTTP API, CLI, MCP server, Python SDK

Built for AI agent builders, RAG infra, and ops teams who don't want to hand-wire search APIs.

Contents

• Quickstart
• Providers
• HTTP API
• Integration
  • CLI
  • MCP
  • Python
• Content Extraction
• Architecture
• Configuration
• FAQ

Quickstart

Mode 1: Local CLI (zero config)

pip install argus-search && argus search -q "python web frameworks"

That's it. DuckDuckGo handles the search — no accounts, no keys, no containers. You get unlimited free search from your laptop right now. Add API keys whenever you want more providers, or don't.

argus extract -u "https://example.com/article"       # extract clean text from any URL

Works on any machine with Python 3.11+ — laptop, Mac Mini, Raspberry Pi, cloud VM. Nothing to host.

For MCP (Claude Code, Cursor, VS Code):

pipx install argus-search[mcp] && argus mcp serve

Then add to your MCP config:

{"mcpServers": {"argus": {"command": "argus", "args": ["mcp", "serve"]}}}

Or install from the MCP Registry:

{
  "mcpServers": {
    "argus": {
      "registryType": "pypi",
      "identifier": "argus-search",
      "runtimeHint": "uvx"
    }
  }
}

One command to install, one JSON block to connect. No server to run, no keys to configure.

Mode 2: Full Stack Server

Got a Raspberry Pi running Pi-hole? A Mac Mini on your desk? An old laptop? That's enough to run the full stack — SearXNG (your own private search engine) plus local JS-rendering content extraction.

docker compose up -d    # SearXNG + Argus

SearXNG takes 512MB of RAM and gives you a private Google-style search engine that nobody can rate-limit, block, or charge for. It runs alongside Pi-hole on hardware millions o

... View full README on GitHub