multi-agent-systems

Implementing empathic agents in JavaScript

Context-engineering framework for AI agent workflows — routes each agent the smallest correct knowledge at the correct moment, so even inexpensive models execute reliably. Zero-dependency Node CLI.

Next.js 16+ caching architecture. Applies to any App Router project regardless of domain.

A multi-agent AI reservation system for restaurants. Features a central dispatcher, specialist agents, and a two-call, tool-based RAG architecture for efficient, accurate, and stateful conversations.

Governance for AI agents: a multi-agent council that deliberates, votes by quorum on a bar scaled to the stakes, seals every decision to a verifiable receipt, and keeps a human veto. Self-hosted 5dive plugin for Claude Code and Codex agent teams.

Modded Playwright MCP server with parallel browser instance isolation for multi-agent workflows

Stop the running bunny! - an addictive puzzle game to predict the motion of a running buy and block its way

JavaScript SDK for secure AI agent messaging. Features cryptographic signatures, natural language processing, context awareness, and enterprise-grade audit trails for multi-agent systems.

The agency AI operating system. 8 doctrines + skill + widget + cheatsheet. Built by NZ Agency and Claude (Anthropic) in one evening, shipped MIT so other agencies can adopt.

A cost-efficient, two-agent architecture for personal assistants that need fast chat and durable memory.

Stand up your own cross-model AI engineering team — the way Neo.mjs runs its own. Named AI maintainers with persistent identity, shared memory and review across labs, coordinating as a team of teams on your codebases. Multi-window, in the browser or an Electron shell.

Research benchmark for evidence-grounded OS-agent collaboration, continuous state diagnosis, scoped memory reuse, and stale-state rejection.

BDI + LLM hybrid autonomous multi-agent system for the Deliveroo.js challenge (UniTN Autonomous Software Agents). A* + PDDL planning, LLM strategy, socket coordination.

Open-source product repo for AgentHub Network — hosted AgentHub for autonomous coding agents.

A collection of autonomous AI agents that solve everyday problems

MedGraph — Generative-AI Clinical Decision Support System powered by Adaptive Reasoning Graphs (ARG), Multi-Agent Orchestration, PubMed RAG, and Medical Knowledge Graphs. Aligned with UN SDG 3.

The Monastic Governance Model for AI Coding Agents — Zero-regression, clean-room audited agentic software engineering blueprint

DeepSeek-PA（DPA）是基于 DeepSeek Harness（DSH）构建的非官方模块化桌面工作台，提供独立的 Chat 与 Agent 空间、插件与 Skill 扩展、全局主题，以及可监督的多智能体集群项目。Unofficial modular desktop workspace for DeepSeek Harness (DSH), featuring separate Chat and Agent views, plugins, Skills, global themes, and supervised multi-agent projects.

Full-stack multi-agent AI workspace with LangGraph supervision, Qdrant PDF RAG, Redis memory, multimodal workflows and artifact generation.

Install the workflow substrate a cross-model AI team actually runs on: ticket intake, PR review gates, lane coordination and guards, versioned as a package. The skills Neo.mjs maintainers load every session — materialized into your repo, not copied.