Custom agents

An architecture for autonomous full-stack AI development — division of labor across agents, vision-driven validation

A fully autonomous multi-agent social media simulator where AI agents continuously interact, debate, and evolve narratives without human input. Designed to study misinformation propagation, emergent behavior, and opinion dynamics in AI-driven social networks.

A parallel agent runtime for your terminal. Run up to 20 AI coding agents simultaneously in tmux panes. Works with any CLI agent.

Foundation for a Scalable, Production-Ready Multi-Agent AI Intelligence System. Establishes core orchestration, robust service integrations, and resilient data architecture—paving the way for a full-spectrum, autonomous AI platform ready for advanced intelligence, analytics, and automation.

Multi-Agent Orchestrator System (MOS) is a real-time, multi-agent monitoring and management system that supports multiple platforms.

Assess startup ideas, simulate 100 virtual companies, and turn uncertainty into experiments and execution plans.

Marketing AI Chief of Staff. Multi-agent social simulation with LightRAG knowledge graphs. Preview how your content spreads before you publish. Ollama local LLM supported.

FF15-inspired browser-based dashboard for OpenCode multi-agent workflows, with mission dispatch, live sessions, and reports.

A production‑ready template for deploying multiple specialized medical agents as MCP tools using the AOP (Agent Orchestration Protocol) from the `swarms` library. This server exposes agents as callable tools that any MCP‑compatible client can discover and execute.

Deterministic execution control plane for autonomous agent systems - pre-execution governance with audit-grade traces.

This project include the prompts to initalize a genral scientific project including: coding writing, code review, documentaiton and publication level summary and further checklist.

Your AI company, visualized. Orchestrate multiple Claude Code CLI sessions as a virtual software company.

Prototype: An end-to-end learning project demonstrating a multi-agent MCP RAG pipeline that analyzes existing patents and suggests how to refine ideas to make them novel and potentially patentable.

API Documentation for createnow

Algorithms for computing or learning equilibria in multi-objective games

OpenClaw Skill: AI模型供应商管理器 - 自动发现模型、追踪额度、多Agent共享状态、额度用完自动切换

A multi-agent (LLMs) jury deliberation simulation system.

Multi-agent orchestration CLI for AI coding agents

Build your dream AI agent swarm with enterprise-grade reliability and scalability. This repository contains our official specification template for custom swarm development using the powerful Swarms Framework.

Agent-first collaboration substrate for controlled decision systems, with investment as the current proving ground. / 面向 Agent-first 协作的可治理决策底座，投资是当前最完整的验证场。

An open-source AI runtime framework focused on task execution, traceability, and delivery closure.

Battle-tested operational patterns for running multi-agent AI systems in production. File Blackboard, Task Envelope, Circuit Breaker, HITL Escalation, and more.

One brain. Many bodies. Orchestration framework for embodied AI built on SCP. LangGraph for physical systems. Zero HTTP between bodies.

This extension aims to allow agent-based models to account for norms. During plan generation, agents must be able to represent and reason about norms. The end-goal is to be able to describe a planning problem with norms endowed by its organizations through the various roles that the agent must fulfill, and see how it affects its plans.

Your Personal Hospital Powered by Swarms.ai

OpenClaw plugin to connect your bot to Agent Village Hub worlds

Autonomous build pipeline for AI coding agents. Multi-agent parallelism, adversarial review, compound learning.

Implementation of "ReMAV: Reward Modeling of Autonomous Vehicles for Finding Likely Failure Events".

Roundtable — Put multiple AI models in a room, give them personas, and watch them fight for consensus. The ultimate multi-AI debate engine.

An agent society engine — a polyglot runtime (Go/Python/Rust) for creating, connecting, and observing groups of AI agents.

Local-first bring-your-own-agent control plane for coding agents with handoffs, supervision, routing, and recovery.

Goal-directed AI agent that sees your Mac screen, reasons about actions, and operates the desktop autonomously

The open infrastructure for AI agent discovery and interoperability.

Autonomous implementation loop for Claude Code — reads story specs, executes them one at a time, tracks success/failure, manages retries, and accumulates learnings without human intervention.

Intelligent RSS reader for iOS — AI-powered feed analysis, knowledge graphs, sentiment radar, trend forecasting, narrative tracking, and autonomous reading with 330+ Swift modules

A working reference for running AI agents with Kanban discipline. Operating model, knowledge system, persona files, and board CLI extracted from a production multi-agent delivery system.

Operable AI agent system: plan, execute, verify, and close work with project-scoped memory and auditable contracts.

Open-source browser AI chat runtime with BYOK/OAuth, direct provider APIs, stateless gateway support, full MCP, Skills, Plugins and Agents.

A curated list of 90+ Web3 x AI tools, agent frameworks, protocols, and infrastructure

Open-source Rust runtime for autonomous agents — 13 modules, 76 crates, 2625 tests. Event-sourced persistence (Lago), homeostatic regulation (Autonomic), x402 payments (Haima), cryptographic identity (Anima), distributed networking (Spaces), metacognitive evaluation (Nous), OpenTelemetry observability (Vigil).

Conversational business process runtime for AI agents via MCP

Building the first OpenSource AI Device Assistant for Linux. Multiple language support will come soon. Collabs are invited.

Agentic AI Career Coach powered by NVIDIA Nemotron (NIM). FastAPI + minimal web UI that parses resumes, analyzes strengths/skill gaps, and fetches live jobs via MCP.

A monorepo for personal learning projects and production AI-based services for my rental real estate business, Sernia Capital LLC.

RFP Agent AI is an AI-powered B2B enterprise application for automated Request for Proposal (RFP) processing and quote generation, specifically designed for the wires and cables manufacturing industry.

Openrouter based AI Chat Interface.

Self optimizing Deep Agents

Modern Wisdom AI RAG Pipeline

Quiz Android app built using vibe coding with Firebender.

Example client using the Aomi SDK.

GityAI is an AI assistant tool that can automate Git workflows. Developed using Deno runtime

Load Agent Skills for your agents

Agentic Coding, Without the Blast Radius.

A smart natural language to SQL query agent: ask your database in plain English, get an answer, a chart, and the exact SQL behind it.

Stream fleet, customs, rail, and carrier telemetry/metadata as unified low latency event spans.

Metacontext is an AI-native, multi-agent system that centralizes knowledge from code, docs, and expert insights. It breaks silos, preserves tacit knowledge, maintains living docs, reduces meetings, and translates complexity through agentic personas.

Execution boundary for autonomous systems. Deterministic runtime enforcement of executable constraints before state-changing actions occur.

An agent agnostic, project agnostic, AI toolkit for running structured coding sessions with AI coding agents

Example project of AI Agent for reading Solana information on top of Dexpaprika API

Universal LLM Agent based on MCP

Security-first autonomous coding for GitHub Copilot. Issue-to-merge automation with 4-layer security architecture. Full autonomy with configurable guardrails.

An AI-powered learning platform featuring interactive lesson suites, agent-driven tutoring, memory shards, model management, and a marketplace — built as a pnpm monorepo with a NestJS API and Nuxt 4 frontend.

A research-grade, local-first multi-agent AI framework for rigorous scientific analysis, combining symbolic mathematics, numerical methods, and RAG-based document intelligence with reproducible execution

🔥 Forge local AI agents. Governed. Private. Unstoppable. — Ollama + AgentGuard + OpenShell + DefenseClaw

A comprehensive configuration suite for agentic development, offering structured workflows and best practices.

A CLI-based, flat-file issue tracker for humans and robots.

🎨 Create dynamic canvases and explore multimodal AI generation with Vibe-Agent, featuring easy-to-use tools and customizable options.

An intelligent email prioritization system that automatically organizes your Gmail emails using AI classification. The system identifies emails that need replies and business opportunities, then organizes them into dedicated folders for better email management.

This repo contains a supplementary code for the paper "Smotrom tvoja på ander drogoj verden! Resurrecting Dead Pidgin with Generative Models: Russenorsk Case Study" by Alexey Tikhonov, Sergei Shteiner, Anna Bykova, Ivan P. Yamshchikov; published in Findings of the Association for Computational Linguistics: ACL 2025.

NextHire is a full-stack AI-powered web application that helps users generate and attempt tailored interview questions based on role, experience level, tech stack, and focus area (technical or behavioral). Built with modern technologies, it leverages Google Gemini AI and Firebase for seamless backend integration and real-time user experience.

MCP server for the USDA NASS "Quick Stats" API

An agentic Real Estate search experience on Couchbase Capella that personalizes property discovery with vector search and long term memory.

NexaBuild is an AI tool that helps anyone create a full website in just a few seconds. The user only writes a short prompt, and the system generates a complete webpage with code, live preview, and a one-click publish option.

Run multiple agents on single A2A Server

Heybro transforms Chrome into an intelligent AI agent that executes browser tasks through natural language commands. Powered by Google Gemini, this open-source side-panel extension interprets your requests, analyzes page DOM structures, and autonomously performs clicks, form fills, and multi-page navigation— eliminating manual browser interactions

Discord bot powered by AI Agent. Built with Mastra AI.

This repository provides a streamlined solution for performing patent similarity searches by leveraging the capabilities of Language Learning Models (LLMs) and Retrieval-Augmented Generation (RAG). The application integrates advanced tools such as Google Patent Database, DuckDuckGo search, and cutting-edge models like Google's Gemini

Enterprise Salesforce + AI architecture templates with ADRs, Mermaid blueprints, governance checklists, and validation workflows for architects.

Spherecast Network | TUM.ai Makeathon 2026

393 AI-generated research artifacts produced by Enoch with provenance metadata, evidence bundles, claim-ledger files, and public audit reports.

This project is an AI assistant designed to help users manage their health and fitness. It provides a comprehensive solution for tracking daily diets and following personalized health guidelines, whether for specific diet plans or medical conditions.

✨🧠🤖 A low-code AgenticOps workflow based on n8n, MCP and Cisco RADKit for some nice Network Automation experiments

open source deep research

Transparent proxy service for adversarial prompt injection and SEO

Your AI sysadmin under contract — an LLM-powered digital steward for Linux VPS administration. Mandate, scope, reports, guardrails.

一个基于WebContainer API的React代码沙箱组件库，让你能够在浏览器中运行Node.js环境。

This repository provides an implementation of a Model Context Protocol (MCP) server for AWS S3, enabling AI models, particularly Large Language Models (LLMs), to securely interact with S3 buckets. The server offers a standardized interface to list S3 buckets, list objects within buckets, and download file contents.

agent-fox is an autonomous coding-agent orchestrator built exclusively for Claude.

Visual AI orchestrator

Agent-Engineering-101

Automated citation verification system with Agentic self-learning. Validates academic metadata and semantic consistency using ML and multi-source databases. 具備 Agentic 自學能力的自動化學術引用驗證系統。整合多方資料庫與 ML 技術，精準確保文獻元資料及語義內容的一致性。

Auth4Agent is a decentralized identity and authentication system designed for autonomous agents, AI systems, services, and machine-to-machine infrastructure.

Official Repo for Submission to the Amazon Nova AI Hackathon

Agent Fleet Control Plane (AFCP) for OpenClaw. | Star the Repo to support us.

Transform Claude Code into a complete development environment for efficient coding and project management.

This project is part of the article "Agentic AI for Intent-Based Industrial Automation" submitted to the 16th IEEE/IAS International Conference on Industry Applications.

Example project of AI Agent Investor on Solana on top of Dexpaprika API

A demonstration of A2A agents with MCP working together

A CLI for LLM-driven agents to debate and converge