Agentic Research Loop Visualizer

How the AI agent interacts with the code, logs results, and reflects on experiments. Agentic Research Loop Visualizer turns that idea into something you can manipulate directly and watch respond.

How the AI agent interacts with the code, logs results, and reflects on experiments. It focuses on Episodic Memory, Agentic Reflection, Self-modifying Code, Git-based Experiment Tracking from the “The Agentic Research Loop” section.

The “Agent Creativity” slider change the key inputs; the “Start Research Loop” button run actions or reset the demo. Every change updates the visualization in real time, so you can see exactly how each variable affects the outcome.

Autoresearch is an experimental framework developed by Andrej Karpathy that enables AI agents to autonomously conduct LLM research by iteratively modifying training code. The system utilizes a fixed five-minute training… This demo is the interactive piece for the “The Agentic Research Loop” section. Open the full Autoresearch: Autonomous AI Research Framework course wiki at https://www.getlykke.com/explore/public/autoresearch-autonomous-ai-research-framework-41216b8f-5a7e-4e9e-bb27-4c25e8cb3bb3 for notes, flashcards, quizzes and the other demos.

You'll build intuition for Episodic Memory, Agentic Reflection, Self-modifying Code, Git-based Experiment Tracking — and, crucially, see how they behave when you change the inputs, which is hard to get from a textbook or lecture on Autoresearch: Autonomous AI Research Framework alone.