SALT-NLP/collaborative-gym
Framework and toolkits for building and evaluating collaborative agents that can work together with humans.
This project helps people work with AI to complete tasks more effectively. You give the system a task like planning a trip, researching a topic, or analyzing data, and an AI agent works alongside you in a shared workspace, exchanging messages and taking actions. It's designed for anyone who needs assistance with complex tasks that benefit from both human insight and AI speed, especially those involved in research, planning, or data analysis.
124 stars. Available on PyPI.
Use this if you want an AI to actively collaborate with you, taking initiative and intervening in real-time, rather than just answering questions like a chatbot.
Not ideal if you're looking for an AI that operates completely autonomously without any human input or a simple question-and-answer tool.
Stars
124
Forks
19
Language
Python
License
MIT
Category
Last pushed
Dec 04, 2025
Commits (30d)
0
Dependencies
23
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/SALT-NLP/collaborative-gym"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
ai4co/reevo
[NeurIPS 2024] ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution
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...
sethkarten/LLM-Economist
Official repository of the 2025 paper, LLM Economist: Large Population Models and Mechanism...