How this analysis was created: This summary and feature list were written by an AI model that read the project's README and public documentation pages. Each feature links to the documentation it came from; stars, license and language come straight from the GitHub API. The model does not read the source code, and the analysis is refreshed when the project is re-analysed. Learn more on our About page.
OpenAGI: When LLM Meets Domain Experts
MLGym A New Framework and Benchmark for Advancing AI Research Agents
Figure 1: Natural Swarm Intelligence Inspiration and SwarmBench Tasks.
Now the official Code for MultiagentBench has been moved to MARBLE
The main features of multiagentbench/marble are: General Agent Benchmarks.
Open-source alternatives to multiagentbench/marble include: agiresearch/openagi — OpenAGI: When LLM Meets Domain Experts. facebookresearch/mlgym — MLGym A New Framework and Benchmark for Advancing AI Research Agents. masworks/x-mas — [2025/05/23] See our preprint paper in ArXiv. ruc-gsai/yulan-swarmintell — Figure 1: Natural Swarm Intelligence Inspiration and SwarmBench Tasks. thudm/agentbench — A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24).