agent-colosseum is an open-source Python framework for orchestrating and benchmarking multi-agent AI systems. It supports agent debates, red-teaming, and peer review, helping researchers evaluate and improve collaborative AI reasoning.
agent-colosseum sits in PulseGate's Multi-agent & orchestration category. It focuses on enabling researchers to benchmark and compare multi-agent AI systems through debate and collaborative reasoning. It is built as an open-source project for AI researchers and developers. agent-colosseum is open source under the MIT license. It ships for the command line, and it can be self-hosted.
jinsoo96 (GitHub) builds and maintains agent-colosseum, and it first shipped in 2026. Development happens publicly on GitHub with 5 commits in the last 90 days. Among its 5 catalogued features are multi-agent orchestration, debate benchmarking, and red-teaming.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do