Olam Labs

Active

Building multi-agent simulations for model evals and training.

S26·Summer 2026·B2B·San Francisco, CA, USA·Team of 2

About

Multi-agent environments let us evaluate and train models in complex, simulated worlds. We work with researchers on both evaluations and training for character and agentic performance typically difficult to assess for using current popular datasets. Play one of our first releases, Multi-Agent Arena (https://olamlabs.ai/arena), where humans come play social strategy games against multiple AI agents. It's currently top 50 on OpenRouter and has thousands of matches played each day. We use Multi-Agent Arena to build datasets on agentic performance and real-world socialization.

Change history · 12 recorded

August 16, 2026
- Tags updated07:00 PM
- Description rewritten07:00 PM
August 12, 2026
- Description rewritten07:00 PM
- Tags updated07:00 PM
August 6, 2026
- Description rewritten07:00 PM
- Tags updated07:00 PM
August 5, 2026
- Description rewritten07:00 PM
- Pitch updated07:00 PM
- Tags updated07:00 PM
August 4, 2026
- Tags updated07:00 PM
August 2, 2026
- Tags updated07:00 PM
July 22, 2026
- Tags updated07:00 PM