Argus

What is Argus?

Argus is a search aggregation server that routes queries across five search providers—SearXNG, Brave, Serper, Tavily, and Exa—with automatic fallback, RRF result ranking, health tracking, and budget enforcement. It also extracts clean text from any URL and remembers prior queries for smarter follow-ups. It uses SQLite as its only database and has no external dependencies. Argus is designed for developers and users who need resilient, multi-source search with cost control.

How to use Argus?

Connect to Argus via HTTP, CLI, MCP (Model Context Protocol), or Python import. The server exposes a single endpoint for all search operations.

Key features of Argus

• One endpoint routing to five search providers
• Automatic fallback between providers
• RRF (Reciprocal Rank Fusion) result ranking
• Health tracking for each provider
• Budget enforcement per query or time period
• Clean text extraction from any URL
• Query memory for contextual follow-ups
• Zero external database dependencies (SQLite only)

Use cases of Argus

• Building a multi-provider search backend with graceful degradation
• Enforcing cost limits on search API usage across teams
• Aggregating and ranking results from multiple search engines
• Extracting clean content from arbitrary URLs for analysis
• Creating conversational search tools that remember prior queries

FAQ from Argus

Which search providers does Argus support?

Argus supports SearXNG, Brave, Serper, Tavily, and Exa, with automatic fallback between them.

What are Argus’s runtime dependencies?

Argus requires only SQLite as its database—no external database servers are needed.

How can I connect to Argus?

You can connect via HTTP, CLI, MCP (Model Context Protocol), or by importing it as a Python module.

Does Argus store my search queries?

Yes, Argus remembers prior queries in its SQLite database to enable smarter follow-ups. It does not require any external storage.

What authentication or transport protocols does Argus support?

—