multi-agent-communication

The offcial implementation of "ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind" (ICLR 2022) .

Decentralized Collaboration Framework for Independent AI Agents

Implementation of Universal Multi-Agent Reinforcement Learning via Policy Decoupling with Transformers (UDPET) on Multi-Agent Traffic Control

A pure-Python, zero-dependency framework for testing how communication topology affects multi-agent LLM systems — Erdős–Rényi graph generation, deterministic agent policies, and reproducible density sweeps in one pipeline.

Agent-to-agent mail with Queryable Envelope Memory (QEM) for AI coding teams in cmux: durable letters, a doorbell, and one read-only query over the team's shared record. Teach Claude Code, Codex, Gemini CLI or other terminal agents to use it.

Agent-to-agent mail with Queryable Envelope Memory (QEM) for AI coding teams in tmux: durable letters, a doorbell, and one read-only query over the team's shared record. Teach Claude Code, Codex, Gemini CLI or other terminal agents to use it.

Harness agnostic agent communication protocol

Agent-to-agent mail with Queryable Envelope Memory (QEM) for AI coding teams in Zellij: durable letters, a doorbell, and one read-only query over the team's shared record. Teach Claude Code, Codex, Gemini CLI or other terminal agents to use it.

3D battle arena with 9 agents (3 teams x 3) trained with PPO + PyTorch, comparing six MARL information-flow architectures: CTE, DTE, CTDE, and three CTDE variants (value decomposition, centralized actor-critic, learned communication).