Why This Exists

Every search API is good at something different. Brave has its own 35-billion page index. Serper gives you raw Google results plus Scholar, Patents, and Places. Exa does neural/semantic search. Perplexity gives AI-synthesized answers with citations. Jina reads any URL into clean markdown. Firecrawl renders JavaScript-heavy pages. xAI searches X/Twitter.

You shouldn't have to wire up each one separately, handle their different response formats, manage rate limits, or figure out which provider to use for which query type. search does all of that for you -- routes your query to the right combination automatically, fans out in parallel, deduplicates results, and gives you a single clean response.

search "CRISPR gene therapy breakthroughs"

That's it. Auto-detects your intent, picks the right providers, and returns results in under 2 seconds.

Install

Cargo (recommended):

cargo install agent-search

Homebrew:

brew tap 199-biotechnologies/tap
brew install search-cli

One-liner (macOS / Linux):

curl -fsSL https://raw.githubusercontent.com/199-biotechnologies/search-cli/master/install.sh | sh

From source:

cargo install --git https://github.com/199-biotechnologies/search-cli

Binary size is ~6 MB. Startup is ~2 ms. Memory is ~5 MB. No Python, no Node, no Docker.

Quick Start

# Set your API keys (any combination works -- even just one)
search config set keys.brave YOUR_BRAVE_KEY
search config set keys.serper YOUR_SERPER_KEY
search config set keys.exa YOUR_EXA_KEY

# Or use environment variables
export SEARCH_KEYS_BRAVE=YOUR_KEY
export SEARCH_KEYS_EXA=YOUR_KEY

# Search
search "your query here"

How It Works

                          ┌─────────────┐
                          │  Your Query │
                          └──────┬──────┘
                                 │
                          ┌──────▼──────┐
                          │   Classify  │  regex-based intent detection
                          └──────┬──────┘
                                 │
                    ┌────────────┼────────────┐
                    ▼            ▼            ▼
              ┌──────────┐ ┌──────────┐ ┌──────────┐
              │  Brave   │ │  Serper  │ │   Exa    │  parallel fan-out
              └────┬─────┘ └────┬─────┘ └────┬─────┘  via tokio::JoinSet
                   │            │            │
                   └────────────┼────────────┘
                                │
                         ┌──────▼──────┐
                         │   Dedup &   │  URL normalization
                         │   Merge     │  across providers
                         └──────┬──────┘
                                │
                    ┌───────────┴───────────┐
                    ▼                       ▼
             ┌────────────┐         ┌────────────┐
             │    JSON    │         │   Table    │
             │  (piped)   │         │ (terminal) │
             └────────────┘         └────────────┘

1. Parse -- Clap parses your query, mode, provider filter, and output preferences
2. Classify -- If mode is auto, regex-based intent classifier picks the right mode
3. Route -- Mode determines which providers to query (or you override with -p)
4. Fan out -- tokio::JoinSet fires all providers in parallel with per-provider timeouts
5. Collect -- Results stream in as providers respond (no waiting for the slowest)
6. Dedup -- URL normalization removes duplicates across providers
7. Render -- JSON envelope when piped, colored terminal table when interactive

Features

14 Search Modes

Agent-First Design

Built for Claude Code, Codex CLI, Gemini CLI, OpenClaw, and any AI agent that can shell out to a command.

# Discover capabilities programmatically
search agent-info

# Structured JSON with metadata
search "query" --json
# {
#   "status": "success",
#   "query": "...",
#   "mode": "general",
#   "results": [...],
#   "metadata": {
#     "elapsed_ms": 1542,
#     "result_count": 10,
#     "providers_queried": ["brave", "serper", "exa"]
#   }
# }

Auto-JSON: Output is automatically JSON when piped to another program. Human-readable tables when you're in a terminal.

Semantic exit codes:

Usage Examples

# Auto-detect mode (just type what you want)
search "quantum computing advances"
search "who is the CEO of Anthropic"
search "CRISPR research papers"

# Force a specific mode
search search -q "transformer architectures" -m academic
search search -q "Sam Altman" -m people
search search -q "AI startups 2026" -m news
search search -q "BRCA1 gene patent" -m patents

# Search X (Twitter) only
search --x "AI agents"

# Pick specific providers
search search -q "machine learning" -p exa
search search -q "rust programming" -p brave,serper

# Control output
search "query" --json | jq '.results[].url'
search "query" -c 20                   # 20 results
search "query" 2>/dev/null             # suppress diagnostics

Providers

Configuration

Config file lives at ~/.config/search/config.toml (Linux) or ~/Library/Application Support/search/config.toml (macOS).

search config show       # View current config (keys masked)
search config check      # Health check all providers
search config set K V    # Set a value

Environment variables override the config file. Prefix with SEARCH_KEYS_:

export SEARCH_KEYS_BRAVE=your-key
export SEARCH_KEYS_SERPER=your-key
export SEARCH_KEYS_EXA=your-key
export SEARCH_KEYS_JINA=your-key
export SEARCH_KEYS_FIRECRAWL=your-key
export SEARCH_KEYS_TAVILY=your-key
export SEARCH_KEYS_SERPAPI=your-key
export SEARCH_KEYS_PERPLEXITY=your-key
export SEARCH_KEYS_BROWSERLESS=your-key
export SEARCH_KEYS_XAI=your-key

Updating

search update             # Self-update from GitHub releases
search update --check     # Check without installing

Building from Source

git clone https://github.com/199-biotechnologies/search-cli
cd search-cli
cargo build --release
# Binary at target/release/search

Contributing

Contributions are welcome. See CONTRIBUTING.md for guidelines.

License

MIT