whereismyai
OASIS
OASIS is a research framework for creating large-scale social interaction simulations with up to one million autonomous agents.
OASIS provides an infrastructure for running Open Agent Social Interaction Simulations that support up to one million agents. It enables researchers to build dynamic environments where agents can exhibit diverse behaviors. The framework facilitates the study of complex social dynamics and large-scale agent interactions. It is designed for researchers focused on behavior prediction, interactive environment construction, and content creation. Users can access documentation, research papers, datasets, and example scripts to begin implementation.
OASIS at a glance
Key features
- Scalable architecture for up to one million agents
- Dynamic simulation environments
- Diverse agent action spaces
- Recommendation system integration
- Research-focused simulation tools
Use it for
- Conducting research simulations
- Building interactive environments
- Generating content
- Predicting agent behavior
Alternatives to OASIS
- CAMEL — Builds complex multi-agent societies for data generation and simulation.
- GOD — Real-time control and intervention for agent simulations.
- Paper2Agent — It enables direct interaction with research papers and automatic result reproduction.
- MiroFlow — Achieves top rankings on multiple agentic benchmarks with modular architecture.
- OpenResearch — Run parallel research workflows locally or on remote compute.
- Arbor — It grows a hypothesis tree and tests changes on held-out data.
- Jevon Tane — It provides a rigorous, pre-registered framework for AI agents to conduct science together.
- Agent Bayes — Builds defensible research mindmaps with page-level citations.
- FAROS — Connects literature evidence, executable plans, and human review into an auditable research loop.
- LLM Wiki Research — Compiles parallel agent research into source-backed markdown knowledge bases.
- Lune — Accesses trusted knowledge from top conference papers for AI agents.
- OpenVLHarness — Lifts six multimodal model backbones by 9.7 to 12.6 points across 22 benchmarks.
All OASIS alternatives