bin123apple/InfantAgent
[NeurIPS 2025] A multimodal agent that can interact with its own PC in a multimodal manner.
InfantAgent is a tool for AI researchers to train and evaluate AI agents that can interact with a computer like a human. It takes in an AI model and provides a virtual desktop environment where the agent can control the mouse and keyboard to perform tasks. The output is a trained AI agent capable of autonomous computer operation.
Use this if you are an AI researcher developing and testing advanced multimodal agents that need to interact directly with a computer's desktop interface.
Not ideal if you are looking for a ready-to-use application to automate personal computer tasks or a simple browser automation tool.
Stars
35
Forks
1
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 25, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/bin123apple/InfantAgent"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ai4co/reevo
[NeurIPS 2024] ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution
SALT-NLP/collaborative-gym
Framework and toolkits for building and evaluating collaborative agents that can work together...
Gen-Verse/LatentMAS
Latent Collaboration in Multi-Agent Systems
lean-dojo/LeanCopilot
LLMs as Copilots for Theorem Proving in Lean
WooooDyy/AgentGym-RL
Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon...