Vibrant Labs

RL environments for long horizon AI Agents

Y CombinatorWinter 2024ActiveB2BInfrastructureDeveloper ToolsGenerative AIReinforcement LearningOpen Source

What they do

Problem

AI agents struggle to reliably complete long-horizon tasks, and there is a lack of strong benchmarks and environments to evaluate and improve these capabilities.

Solution

Vibrant Labs builds specialized reinforcement-learning environments and benchmarks to train, test, and improve long-horizon browser and computer-use AI agents.

Who it's for

AI research teams and developers building and evaluating browser/computer-use agents.

Founders

Jithin James

Founder

Jithin James (jjmachan), believes that life's purpose is found in the toil in mastering a craft and the fulfilment one gets from using it for the greater good. For him, this means excelling in software development, particularly in open-source and AI tooling, to empower fellow developers and help materialize their ambitious visions into reality. His journey is a testament to skill, dedication, and a commitment to community enrichment.

LinkedIn · X

Shahul ES

Founder

Shahul (aka ikka) discovered his fascination for AI in his sophomore year while pursuing his computer science degree. This early interest laid the foundation for his journey to becoming a Kaggle GrandMaster and led to his significant contributions to open-source AI, particularly in initiatives like OpenAssistant AI.

LinkedIn · X