Installation

import { Aside, Steps, Tabs, TabItem } from ‘@astrojs/starlight/components’;

Option A: Local Installation

1. Clone the repository

   git clone https://github.com/pepetox/osint-ai-one.git
   cd osint-ai-one

2. Create and activate virtual environment

   python -m venv .venv
   source .venv/bin/activate  # Linux/macOS
   # .venv\Scripts\activate   # Windows (PowerShell)

3. Install the package

   pip install -e .

   This installs the package in editable mode and registers the entry points: osint-agent, osint-mcp, osint-a2a.

4. Configure environment variables

   cp .env.example .env

   Edit .env with your preferred editor. At minimum, add one API key:

   # .env — minimum to get started
   VIRUSTOTAL_API_KEY=your_key_here
   
   # Local LLM (default)
   LLM_PROVIDER=ollama
   OLLAMA_MODEL=qwen3:14b

5. Pull the Ollama model

   ollama pull qwen3:14b

6. Verify the installation

   osint-agent --help

   You should see the CLI help menu.

Option B: Docker

```bash git clone https://github.com/pepetox/osint-ai-one.git cd osint-ai-one cp .env.example .env # Edit .env with your API keys

docker compose run --rm --profile cli osint-agent
```

```bash docker compose --profile server up -d ``` - MCP Server: `http://localhost:8080` - A2A Server: `http://localhost:9000` ```bash docker compose run --rm --profile cli osint-agent -q "Investigate IP 8.8.8.8" ```

The Docker image pre-downloads the embeddings model (~100 MB) at build time, so it works offline for the investigation features. The LLM model (Ollama) is downloaded separately.

Verify the installation

# The agent should start without errors
osint-agent

# In the interactive prompt, try a simple query
osint> Investigate IP 8.8.8.8

If you see Ollama connection errors, make sure the service is running:

ollama serve  # In another terminal if not running as a service
ollama list   # Verify the model is downloaded