shizhl/CoAgents
Official code for paper "Learning to Use Tools via Cooperative and Interactive Agents"
Implements a three-agent architecture where a grounding agent generates tool instructions, an execution agent performs API calls, and an observing agent extracts relevant results—with iterative adaptation based on environment feedback. Built on LangChain and integrates with OpenAI LLMs (gpt-3.5-turbo) and external APIs like TMDB, supporting multi-key rotation for quota management across API requests.
221 stars. No commits in the last 6 months.
Stars
221
Forks
2
Language
Python
License
—
Category
Last pushed
Mar 26, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/shizhl/CoAgents"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
google-deepmind/concordia
A library for generative social simulation
Mai-xiyu/Minecraft_AI
AI Play Minecraft
mikelma/craftium
A framework for creating rich, 3D, Minecraft-like single and multi-agent environments for AI...
cocacola-lab/MineLand
Simulating Large-Scale Multi-Agent Interactions with Limited Multimodal Senses and Physical Needs
Dominien/brunnfeld-agentic-world
Medieval village economy simulation — up to 1000 LLM agents across multiple villages, driven by...