Quickstart

Prerequisites

Before installing Parallel Research, make sure you have:

• Rust 1.86+ — required for building from source (skip if using the curl installer)
• API key — for your chosen LLM provider (DeepSeek, OpenAI, Anthropic, etc.)
• Optional: Chrome with --remote-debugging-port=9222 for browser tools

curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh

Installation

Option A: Curl Script (Recommended)

The fastest way to install. Downloads a pre-built binary for your platform.

curl -sSf https://parallel.research/install.sh | sh

This installs the parallel binary to ~/.local/bin. Make sure it's in your PATH.

Option B: Cargo Install

Build from source using Cargo. Requires Rust toolchain.

cargo install parallel-research

Option C: Build from Source

Clone the repository and build locally for development.

git clone https://github.com/parallel-research/parallel-research.git
cd parallel-research
cargo build --release

The binary will be at ./target/release/parallel-research.

First Run

Run your first research session with a single command:

parallel-research run "Find B2B SaaS startups in Berlin with 10-50 employees"

On first run, Parallel Research will prompt you for your API key if one isn't configured. Results are saved to ./research-output/ by default.

Configuration Basics

Configuration is stored in ~/.parallel-research/config.toml. All sections are optional — missing fields use defaults.

Config Location

~/.parallel-research/config.toml

LLM Section

The only required configuration is your LLM provider settings:

[llm]
provider    = "deepseek"
base_url    = "https://api.deepseek.com"
api_key     = "sk-your-key"
model       = "deepseek-v4-flash"
max_tokens  = 8192
temperature = 0.7

Search Backend

Choose a search engine for web queries. hybrid uses the first configured backend with results:

[search]
backend = "hybrid"

[search.tavily]
api_key = "tvly-your-key"

TUI Mode

Launch the interactive terminal UI for a real-time research experience with progress tracking, tool call visualization, and conversation history.

parallel-research tui

The TUI provides an interactive chat interface where you can type queries, watch agent progress in real time, and browse results.

HTTP Server Mode

Start an HTTP API server for programmatic access. Supports REST endpoints and SSE streaming for real-time event delivery.

parallel-research serve

The server starts on http://localhost:8080 by default. Send research requests via POST:

curl -X POST http://localhost:8080/api/v1/sessions \
  -H "Content-Type: application/json" \
  -d {`'{"query": "Find AI startups in London"}'`}

Next Steps

Now that you have Parallel Research running, explore these topics: