facebookresearch/meta-agents-research-environments
Meta Agents Research Environments is a comprehensive platform designed to evaluate AI agents in dynamic, realistic scenarios. Unlike static benchmarks, this platform introduces evolving environments where agents must adapt their strategies as new information becomes available, mirroring real-world challenges.
The platform implements a modular architecture with agents executing ReAct-based reasoning over interactive apps (email, calendar, file system) that generate dynamic events to create evolving scenarios. It provides 800+ benchmark tasks across the Gaia2 dataset accessible via CLI or web GUI, with multi-model support through LiteLLM covering Llama, local deployments, and other providers for standardized agent evaluation.
447 stars and 2,569 monthly downloads. Available on PyPI.
Stars
447
Forks
60
Language
Python
License
MIT
Category
Last pushed
Mar 11, 2026
Monthly downloads
2,569
Commits (30d)
0
Dependencies
22
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/facebookresearch/meta-agents-research-environments"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related agents
openai/openai-agents-python
A lightweight, powerful framework for multi-agent workflows
openagents-org/openagents
OpenAgents - AI Agent Networks for Open Collaboration
camel-ai/camel
🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents....
vamplabAI/sgr-agent-core
Schema-Guided Reasoning (SGR) has agentic system design created by neuraldeep community
BrainBlend-AI/atomic-agents
Building AI agents, atomically