Forsy-AI/biosecurity-agent

Biosecurity Agent Harness v0.1

AI agent that builds a live biosecurity world around any target.

Quick Start

npx @forsy/biosecurity-agent

Configure your AI agent. Tell it what to protect. It starts investigating and tracking automatically.

Start with one target or a connected set, then refine them conversationally as the world changes. The terminal exposes each real processing lane from discovery and retrieval through claim extraction and synthesis while keeping the underlying evidence inspectable. Exit whenever you like; the local runtime restores the same targets, watchers, and world on your next launch.

1. Define targets

Describe people, animals, plants, products, places, organisations, or multiple connected targets in ordinary language. Files, private context, public URLs, and custom sources can add the details that make evidence relevant to you.

2. Live biosecurity

Your agent tracks official and scientific sources, news and the open web, public OSINT, sensors and surveillance, and connected data. It builds a target-centred biosecurity world, links evidence across places and time, and keeps that world updated in the background.

3. Predict + protect

From the current live state, the agent can simulate forward and recommend defensive actions backed by inspectable evidence. Observed, inferred, and simulated claims always remain distinct.

Terminal

This excerpt comes from the persisted run shown above:

TARGET MODELLING          ✓ 3 targets
OFFICIAL + SCIENTIFIC     ✓ 5 sources
NEWS + OPEN WEB           ✓ 4 sources
SOCIAL + COMMUNITY        ✓ 3 sources
SENSORS + SURVEILLANCE    ✓ 4 sources
CUSTOM SOURCES            ✓ 2 sources
WORLD SYNTHESIS           ✓ 18 entities · 18 relationships
LIVE WATCH                ● 3 watchers

SIMULATION · +14 DAYS
London household · Milo · Heathrow → Singapore
3 future paths · 1 protection · 3 evidence links