Gen-Verse/LatentMAS
Latent Collaboration in Multi-Agent Systems
This project helps AI developers and researchers create more efficient and powerful multi-agent AI systems. Instead of agents communicating with verbose text, LatentMAS enables them to share concise "thoughts" (latent states). This results in faster processing, lower token usage, and overall better performance for complex, multi-step AI reasoning tasks.
800 stars. Actively maintained with 2 commits in the last 30 days.
Use this if you are building multi-agent AI systems for tasks like scientific discovery, complex problem-solving, or code generation and need to significantly improve their speed and reduce computational costs.
Not ideal if you are working with single-agent AI systems or require agents to communicate using human-readable text for auditing or direct human interaction.
Stars
800
Forks
119
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 27, 2026
Commits (30d)
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/Gen-Verse/LatentMAS"
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
SALT-NLP/collaborative-gym
Framework and toolkits for building and evaluating collaborative agents that can work together...
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...