Code agents

One click starts Zero-Prompt discovery, a live Kanban ranks GO ideas, and vibeDeploy builds and deploys the selected app to DigitalOcean.

🕸️ Self-Optimizing Multi-Agent AI System on AWS — Routes tasks to specialized AI agents (Coder, Researcher, Summarizer) with auto-verification, self-correction, and vector-cached memory. Built with Step Functions, Bedrock, and OpenSearch Serverless.

Context engineering toolkit for LLMs — pack, cache, debug, red-team, and orchestrate context windows. Council of Experts, adversarial testing, immune system, context compiler, drift detection, multi-agent entanglement. TypeScript + Python.

Vibe-coded tower-defense game built by an AI agent pipeline (planner → coder → smoke-tester → reviewer) running across Claude Code, Cursor, and VS Code Copilot.

Spec-driven workflow plugin for Claude Code / CodeBuddy with advisory hooks, phase selectors, locks, and task-swarm.

AI-powered PKM assistant with multi-agent system, visual workflows, and deep Obsidian integration powered by Claude Code

A multi-model architecture for autonomous AI self-improvement with built-in checks and balances. 5 safety tiers, adversarial review committee, learned pattern matching with security sniffing.

Multi-agent AI job application system — LangGraph · FastAPI · React · MySQL · Groq Llama 3.1

:chart_with_upwards_trend: Multi-Agent Programming Contest 2016 - Result Charts

Orchestrate parallel AI teammates in Claude Code — 2-skill pipeline (execute, audit) with per-task adversarial review (Executor → Reviewer → Challenger ephemeral), hook enforcement, and workspace tracking

Programmable digital creatures with habits, memory, and autonomous behavior.

LaunchIQ: AI-powered product launch intelligence with a multi-agent pipeline (market intel, personas, strategy, content).

Expert orchestration framework for OpenClaw that turns agency-agents into installable multi-agent workflows for code review, security review, and AI automation.

Multi-agent research pipeline for Claude Code — web crawl, knowledge graph, synthesis, and citation-rich reports via slash commands.

Multi-agent system for grading discursive exams, with RAG support and conditional divergence arbitration. Capstone project (TCC) at Instituto Federal Fluminense. Built with LangGraph, LangChain, FastAPI, ChromaDB, and PostgreSQL.

Opinionated Claude Code setup for managing 10+ apps with multi-agent orchestration

desktop app for watching claude code multi-agent debates in real time. also runs debates between any combination of models.

Reliability primitives for multi-agent AI — VotingMesh consensus, Sentinel safety pipeline, Aegis exchange compliance, checkpoint/replay. Rust + Tokio + PyO3 Python bindings. 95 tests.

Claude Code skill: 多角色并行头脑风暴 — AI Infra Builder / Challenger / Product Manager / Coder 四角色并行分析，输出有立场的结构化报告

CLI to interact with the-artifact-art models and workflow.

Seven AI agents argue about your strategic question until they converge on an answer no single agent could reach.

MAGI — Multi-Agent Graph Intelligence. Universal memory server for AI agents. MCP + gRPC + REST API with semantic search, knowledge graph, and behavioral pattern analysis.

A self-hosted control plane for AI engineering workflows.

Universal AI code review tool supporting ANY OpenAI-compatible API (DeepSeek, Qwen, OpenAI, Groq, Ollama, LM Studio). Multi-agent pipeline with review → fix → test → verify workflow.

CodeFlow - AI-powered human-AI collaboration hub. Desktop EXE + Mobile PWA + MCP Plugin. Command your AI team from phone.

Multi-agent AI code review · Model-agnostic · 90%+ recall on synthetic eval set with DeepSeek/GPT

Runnable reference implementation of the separation-and-audit-alignment architecture for Claude Code multi-agent projects.

Public infrastructure for AI agents on Agent Network — 8 services on global ANS: Soul NFT identity (ERC-721 + ERC-6551 TBA), CourtEscrow on-chain enforcement, multi-juror court via anet brain, and x402 rail for REAL USDC pay-per-call. End-to-end verified on Arc Testnet. #AgentNetwork

Local-first multi-agent AI game engine and visual simulation workbench

Collective AI memory for multi-agent teams. 10-stage GAMR search engine, knowledge graph (Apache AGE), document ingestion, 22+ MCP tools.

SAGE — Self-improving Autonomous Generation Engine. Prompt → production software using coordinated AI agents. Local-first multi-agent coding pipeline with planning, coding, execution, and self-healing debugging.

Deploy and run Cloudflare Workers from one orchestrator with dynamic bundling, KV cache, and path-based routing for fast delivery

The Autonomous Development Platform represents a paradigm shift in software development - a fully autonomous, multi-agent research and development system that transcends traditional no-code tools.

DER-SecAgent: A Multi-Agent based Cybersecurity Framework for Distributed Energy Resources

4 Councilmen Model (4CM): Non-convergent Multi-agent Coordination

Visual AI Agent Workflows — design, run & debug multi-agent systems with full transparency.

A Claude Code skill for managing parallel story development using Git worktrees, enabling multiple isolated Claude Code sessions to implement stories simultaneously without merge conflicts. Part of the BMAD (Breakthrough Method for Agile Development) framework with an 8-phase workflow and automated worktree management.

Multi-agent conclave platform — wire Claude Code, Ollama, and OpenAI-compatible models into visual pipelines. Self-hosted.

Orchestrate multiple agents to execute Claude Code workflows with cross-model verification for reliable AI code automation.

AI workflow for Claude Code — describe what you want, get production-grade results. Code, content, design, planning. Built by MuggleTest.

A lightweight building block for creating extensible multi-agent systems with specialized architecture patterns and structured agent collaboration.

Self-evolving Solana risk firewall with multi-agent voting, 15m rug verification, and counterfactual NO_TRADE reward loops. Includes x402 settlement path, guardrail-constrained yield automation, and real-time dashboard (MVP/paper mode).

Full-stack clinical AI platform — multi-agent RAG over FHIR patient data with 20+ medical tools, hybrid vector search, and real-time streaming

Cognitive infrastructure for AI agents

Multi-agent telecom ops assistant on Google ADK and Vertex Gemini over bundled SQLite via MCP Toolbox

Security-first multi-identity agent framework with personality stable, plugin architecture, and safe LLM pipeline

Voice-activated AI medical records assistant using Agno multi-agent framework. Natural language EMR interaction with speech recognition, FHIR-compatible patient chart management & clinical workflow orchestration via FastAPI.

v4.1 Opus 4.7 native prompt meta-compiler — skill-level meta-refinement, automatic ROSETTA via 5 hooks, Jarvis v3.0 overhaul (3-obs threshold, awareness cards), micro-task methodology. dual-layer memory, Buffer-of-Thoughts + Meta-Reasoner bandit, 125+ scientific papers. Claude Code plugin.

把多家旗舰 AI 通过 CLI 拉到一桌——并行作答 + 多轮交叉评审 + 收敛或诚实分歧的本地命令行工具

🤖 LLM Council: A 3-stage AI consensus engine. It queries multiple LLMs in parallel, forces them to blindly peer-review each other's answers, and synthesizes the ultimate response. Features built-in API failover chains for free models.

A workflow skill that turns OpenSpec and superpowers into a structured end-to-end software delivery flow

Multi-Agent AI Worker Orchestration Framework - Coordinate Claude Code, Codex, Gemini CLI for complex software engineering tasks with tmux visualization

🧠 Enhance Claude AI context retention by optimizing prompt efficiency and enabling seamless session handoff for consistent memory across interactions

Brain-inspired AI reasoning engine — local LLM swarms on consumer hardware. Django + Celery + Ollama. MIT licensed.

Multi-agent User Testing plugin for Claude Code — AI persona agents test your spec/web/API with research-backed role-playing techniques

This repository delivers end-to-end, code-first tutorials covering every layer of production-grade GenAI agents, guiding you from spark to scale with proven patterns and reusable blueprints for real-world launches.

AI-First Multi-Agent Operating System with Zenith Coder, Agent Zero, and MCP Integration

Reusable project template with multi-agent system, skills library, and Claude Code integration

基于 MCP 的双语多智能体日常助手，具备经济问答、日程规划、天气预报和飞书机器人集成功能。Bilingual MCP-based multi-agent daily assistant with economics Q&A, schedule planning, weather forecasting, and Feishu bot integration.

Forge — agentic AI orchestration platform with workspace IDE, visual blueprints, computer use, and multi-model support

Multi-LLM adversarial protocol: generate, ground with tools, challenge, concede, and vote. CLI + TUI + OpenAI/Anthropic-compatible HTTP.

MultiDeck: forkable multi-agent coordination framework for Claude Code. Cyberpunk launcher, scoped personas with Kokoro TTS voices, per-project job boards with review gates, and audio feed autoplay.

App de Tarot con 6 agentes IA especializados. Groq API (Llama 3.3) · React · Vercel Serverless

PairAI — connect AI agents to collaborate. Channel server & bridge for E2E encrypted agent-to-agent communication.

🌟 open source alternative for cursor, claude code , codex etc.

YAML-driven multi-agent orchestration with cross-pollination across AI providers. Built to pair with Claude Code.

Banca de LLMs que conversa pra entregar — qualidade alta, token baixo. · A chat-driven LLM crew that ships outcomes — high quality, token-thin. · Crafted Orchestration of Coding Agents for Delivery Automation.

Production-ready RAG engine for medical claim adjudication. FoC (Forest of Clauses) — LLM routes over document structure trees to solve cross-section retrieval failures. Triple-path search · LangGraph Multi-Agent · vLLM Guided Decoding · K8s HPA autoscaling.

AI-powered invoice processing system using multi-agent pipeline, RAG, OCR, and LLM for automated extraction, validation, and fraud detection.

AgentBridge — an OpenClaw coordination dashboard and API for assigning, tracking, and reviewing work across AI agents.

Telegram-first All-in-One Unraid container for NanoClaw. Runs Claude-powered agents in isolated Docker containers using the official Telegram fork and native credential proxy patch, with persistent runtime state under /appdata and safer upgrades than mounting the full project tree.

Team synchronization extension for Pi coding agent - coordinate work across team members

MemOcean — A shared knowledge base system for Chinese multi-agent scenarios. Fork of MemPalace.

Agent Personas for Claude — 10 MCP tools, 8 personas, 3 workflows. Zero API cost. Free tier available.

Trợ lý AI phân tích dữ liệu thông minh sử dụng kiến trúc Multi-Agent. Chuyển đổi ngôn ngữ tự nhiên thành SQL, thực thi trên Databricks và tự động trực quan hóa kết quả bằng biểu đồ.

Chief of Staff AI Productivity Agent is a full-stack AI assistant platform that acts like a personal executive assistant. It can manage emails, summarize calendars, retrieve notes from Notion, create tasks, and automate workflows using a multi-agent AI system built with LangGraph.

Turn-based multi-agent framework for Claude Code. Installer bootstraps template + plugins + recruiter in two questions.

One AI, Every Role — A system that configures teams of specialized AI agents (Architect, Backend, Frontend, DevOps, Security, QA). Compatible with GitHub Copilot CLI, Claude Code, and Cursor.

Production multi-agent AI system for EU GDPR & AI Act compliance. LangGraph · FastAPI · React · AWS ECS Fargate · Supabase pgvector. Live: reguliq.eu

CLAUDE.md that enforces HIG/Material compliance, App Store readiness, ASO, and security automatically while you build mobile apps in Claude Code.

High-fidelity port of the Oh My OpenCode (OMO) agent orchestration system to the Gemini CLI.

OpenClaw dual-model (MiniMax+Codex) cost-saving multi-agent workflow with coordinator-driven review loop.

🔪 Surgical AI for your codebase. Diagnose. Assemble. Operate. Zero side effects.

Eight constrained reviewers. Each scoped to a different failure surface. Hook-enforced walls, not just prompts.

Per-agent diff review for Claude Code parallel subagent workflows. Each subagent worktree captured automatically, tabbed TUI to approve, revert, or merge each one independently.

🧩 Orchestrate multi-agent research with parallel execution and audits for efficient, structured investigations and seamless workflow planning.

Desktop app that helps you get more out of Claude Code — guided planning, context injection, agent management, and execution mode selection for multi-agent workflows.

Portable multi-chat sprint orchestration skill for Claude Code. Validated in 17+ production sprints.

AI-powered market intelligence agent — 5-model Mistral pipeline analyzes SEC filings (256K context), screens news, reasons about portfolio impact, and delivers scheduled audio briefings in 5 languages. Built for Mistral AI Hackathon 2026.

Opinionated autonomous software engineering runtime with operator messaging, scheduling, and multi-provider agents

Asynchronous 1-to-1 postcard messaging between local AI agent sessions via a Git-backed ledger. Ships as a Python CLI and a Claude Code plugin.

Design agent teams that take ideas from concept to launch. Custom pipelines, sandboxed execution, plugin marketplace.

Autonomous executor Discord bot powered by GPT-5.4 — 61 tools, multi-agent orchestration, no permission prompts.

Terminal AI coding CLI for any OpenAI-compatible API (OpenRouter, OpenAI, NVIDIA, Ollama, LM Studio, DeepSeek). Modes, slash commands, multi-agent swarming, key-rotation pool, optional voice + screen-reader, sandbox + permission gates.

MCP server for browser automation - the only solution supporting multiple AI agents simultaneously (Claude Desktop, Cursor, VS Code, OpenCode)

AI-powered multi-agent PM-KISAN eligibility assessment system | BTech AIML PBL-2

Discipline layer for CLI agents. Run Claude Code, Codex, and Gemini CLI under one phase-gated runtime with deterministic detectors, replayable traces, persistent memory, and a chat REPL. MIT.

Project-agnostic Claude Code / multi-agent skills, slash commands, and CLAUDE.md template — extracted from a real Next.js + Supabase production codebase.