allenai/discoveryworld
A virtual environment for developing and evaluating automated scientific discovery agents.
DiscoveryWorld provides a virtual environment for researchers and developers to create and test AI agents capable of scientific discovery. You input an AI agent and it simulates how that agent performs in various scientific tasks, like proteomics or biology. The output helps you understand your agent's problem-solving capabilities and limitations.
200 stars. No commits in the last 6 months. Available on PyPI.
Use this if you are developing or evaluating AI agents designed to perform complex scientific problem-solving or discovery tasks in a simulated environment.
Not ideal if you are looking for a tool to perform actual scientific experiments or data analysis in a real-world setting.
Stars
200
Forks
19
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 10, 2025
Commits (30d)
0
Dependencies
8
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/allenai/discoveryworld"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
openai/openai-agents-python
A lightweight, powerful framework for multi-agent workflows
openagents-org/openagents
OpenAgents - AI Agent Networks for Open Collaboration
vamplabAI/sgr-agent-core
Schema-Guided Reasoning (SGR) has agentic system design created by neuraldeep community
BrainBlend-AI/atomic-agents
Building AI agents, atomically
camel-ai/camel
🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents....