zju-vipa/Odyssey
Odyssey: Empowering Minecraft Agents with Open-World Skills
This project helps researchers and developers create and evaluate advanced AI agents for the open-world game Minecraft. It takes in game environment data and instructions, and outputs actions that enable the agent to perform complex tasks like crafting, combat, and autonomous exploration. The primary users are AI researchers focused on large language models and reinforcement learning within game environments.
368 stars.
Use this if you are an AI researcher developing or testing intelligent agents that need to navigate and interact skillfully within complex, dynamic virtual worlds like Minecraft.
Not ideal if you are looking for a ready-to-play AI bot for personal Minecraft gameplay or a simple game automation tool.
Stars
368
Forks
21
Language
Python
License
MIT
Category
Last pushed
Oct 22, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/zju-vipa/Odyssey"
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...