A python library built on top of UKAISI Inspect to support Control research, by Redwood

Research developing AI control protocols using task decomposition

🚦🗺️ UrbanFlow AI is a web app for generating 3D traffic simulations from real OpenStreetMap areas. It builds SUMO scenarios, runs microscopic vehicles, pedestrians, buses and trams, edits road events, controls real traffic lights with TraCI, trains JSON AI policies, saves models, and shows live metrics, charts, and notebooks.

An intelligent traffic management system that dynamically adjusts highway lane configurations using AI-powered congestion detection and a movable median barrier.

Python client for Aegis — stabilize AI systems instantly with a simple API call.

In-depth exploration of Large Language Models (LLMs), their potential biases, limitations, and the challenges in controlling their outputs. It also includes a Flask application that uses an LLM to perform research on a company and generate a report on its potential for partnership opportunities.

Judge-first framework where LLM outputs must converge under explicit, adversarial oracles.

Independent AI governance and control standard

AI Governance — human-controlled code injection with oversight

Kho lưu trữ này chứa tài liệu, bài tập, và mã nguồn liên quan đến môn Trí tuệ nhân tạo trong điều khiển. Môn học tập trung vào ứng dụng AI trong các hệ thống điều khiển tự động, bao gồm lý thuyết và thực hành.

Lichtarbeit

GG Tank Watch - frozen public-information archive of a resolved May 2026 chemical emergency. Conduit-only design; responsible-AI safety patterns enforced in code and tests.

The project evaluates whether a lightweight hardening layer can recover robustness without redesigning the surrounding protocol. The method combines transcript sanitization, explicit instruction-data separation, and an optional prompt-diversity ensemble.

AutoRed: Measuring the Elicitation Gap via Automated Red-Blue Optimization — AI Control Hackathon 2026

Non-throne AI governance canon for anti-capture, provenance grounding, advisory-only alignment, challenger comparison, and external origin-coordinate evaluation.

Homebridge plugin for ai-control fans

A compact AI-control benchmark for trusted monitoring of untrusted coding agents.

Control protocols robust to a monitor-aware adversary — empirical AI-control eval on the APPS backdoor testbed (open-weight models).

Trace-based agent safety monitor trained on malicious PyPI packages

Gesture-Based PC Controller lets you control your computer with hand gestures using your webcam. It uses computer vision to enable hands-free actions like moving the mouse, scrolling, and adjusting volume or brightness.