xlang-ai/OSWorld
OSWorld is a NeurIPS 2024 benchmark for evaluating multimodal agents on open-ended tasks in real computer environments.
OSWorld is a NeurIPS 2024 benchmark for evaluating multimodal agents on open-ended tasks in real computer environments.
Pricing label: see the product site.
Open xlang-ai/OSWorldIs this your tool? Feature it
More in this area
AI Agents & Workflows
Agency Orchestrator
Build multi-agent workflows using YAML and conditional execution.
See siteVisit
AI Agents & Workflows
Agent Coordinator
Coordinate Codex tasks with dependencies, saved state, and completion checks.
See siteVisit
AI Agents & Workflows
Agent Zero
Create autonomous AI agents with customizable goals and tasks.
See siteVisit