cooperative-ai

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

A decentralized agent network for building collaborative, LLM-powered agent-to-agent (A2A) systems.

AAAI24(Oral) ProAgent: Building Proactive Cooperative Agents with Large Language Models

Synthora is a lightweight, extensible framework for LLM-driven agents and ALM research. It provides the essential components to build, test, and evaluate agents, enabling you to assemble an agent with a single configuration file. Our goal is to minimize effort while delivering robust functionality.

[CVPR 2026] TeamHOI: Learning a Unified Policy for Cooperative Human-Object Interactions with Any Team Size

[ICML 2025] Official Code of SMPE: "Enhancing Cooperative Multi-Agent Reinforcement Learning with State Modelling and Adversarial Exploration"

Exploring techniques to generate diverse conventions in multi-agent settings

Cooperation and Fairness in Multi-Agent Reinforcement Learning

Cooperative Multi-Agent Reinforcement Learning (MARL) Shapley value credit assignment engine evaluating fair marginal agent coalition rewards.

Cooperative Multi-Agent Reinforcement Learning (MARL) Shapley value credit assignment engine evaluating fair marginal agent coalition rewards.

Coordinated multi-agent systems that learn to solve complex collaborative and competitive tasks.

machine learning for blockchain

Camel AI context pack for Claude Code, Codex, Cursor, and Aider: AGENTS.md, CLAUDE.md, prompts, evals, pitfalls, and verification notes for camel-ai/camel.

Carbon-Silicon Symbiotic Civilization: 碳基-硅基-共生文明的理论框架与行动纲领。

CCNETS is uniquely crafted to emulate brain-like information processing and comprises three main components: explainer, producer, and reasoner. Each component is designed to mimic specific brain functions, which aids in generating high-quality datasets and enhancing the classification performance

Official website for VOLPAROSSA's open-source Decentralized Intelligent Cooperative Network (DICN). Explore its mission, shared connectivity, private storage, cooperative AI, application projects, verified development progress and ways to contribute. Lightweight, privacy-conscious HTML/CSS site on GitHub Pages.

Cooperative multi-agent controller for Pokémon Showdown multi battles with CTDE training, intent exchange, benchmarks, and replay analysis.

A research programme on cross-class governance for humans, advanced AI systems, and ecological systems — hub paper + preprint.

Multi-agent elevator dispatch with QR-DQN and CTDE (Centralised Training, Decentralised Execution) in PyTorch. Three cooperative elevators trained with dueling networks, prioritised replay, and a centralised critic — beating ETA-Dispatch by 27% wait and 9.6% energy across 3,500 episodes on a non-uniform 10-floor traffic environment.

Boundary enforcement and disjoint-consent infrastructure for agentic collectives. 15-rule decision engine, MCP pre-flight gateway, tamper-evident ledger, and 50-scenario red-team benchmark.