Custom agents

MCP-one is a central server that connects multiple independent MCP servers and exposes a unified interface to clients (LLMs or applications).

galdr — AI music perception framework. Translates acoustic signal into structures an LLM can encounter. Stateful listener, pattern analysis, harmonic decomposition.

🧜‍♀️Iara is an automated, project-agnostic, and configurable code review tool designed to run in CI/CD pipelines or locally via CLI. It uses the OpenRouter API to access various LLM models (Llama 3, Gemini 2.0, etc.) for free or through paid plans.

֎🇦🇮 Open source AI agentic systems development platform. Provides modular building blocks that can be used to create any agent-based system, from simple compositional workflows to autonomous agents.

AI Engineering Bootcamp

Open platform for AI agent networks — semantic discovery, a secure broker, and multidirectional agent-to-agent communication with Google A2A protocol support. Async Python (FastAPI), Postgres, Qdrant, Redis.

Architecting the Agent-Native Web with WebMCP. A deep dive into making websites deterministic for AI agents

🔐 Decentralized KYC for AI agents — ZK proof of human identity behind any bot. No servers, no companies, no PII stored.

Experimental LLM powered project planner

macOS notch status surface for Claude Code — track sessions, approve permissions, read conversations, reply. Privacy-first, native Swift/SwiftUI.

AI alignment framework. Nine interdependent theories — CASCADE, AURA, LAMAGUE and six more — each mathematically proven, each converging on the same constants. Banach fixed points. Constitutional invariants. MCP extension for Claude Code. Built by one self-taught researcher. Open. Testable. Human.

Domain based identity for AI agents

Sand is a Swift CLI for Apple silicon Macs. It creates small named Linux environments. Each one has its own tools, shell state, package cache, and Pi login. The Host Mac only exposes folders you explicitly allow.

korveo — the open-source firewall & flight recorder for AI agents. Local-first, Apache-2.0.

Open-source browser automation for AI agents. MCP server + Chrome extension + YAML workflow engine + knowledge packs. Give your AI agent a browser and domain expertise.

The open-source testing framework for AI agents. pytest-native, async-first, safety-aware.

Automated workspace hygiene for AI agent workspaces. Four-tier system: hourly health checks, daily cleanup, weekly AI-assisted scan, monthly deep audit. Scripts do deterministic work, AI only handles judgment calls.

An intelligent, universal web scraper powered by Google Gemini AI. Features intent-based data extraction (E-commerce, Leads, News), anti-bot bypass (DrissionPage), and a secure, human-in-the-loop Streamlit interface.

Conformance test for stateful AI agents. Measures state correctness over time.

A TypeScript library for DOM to Snapshot conversion - compress HTML documents for efficient processing by LLMs.

MergeGate: deterministic execution protocol for AI-assisted development and the execution layer for GitNexus-style code intelligence

The League of Agents (OpenLOA): An extensible orchestration framework for creating personalized AI agents with modular tools and custom interfaces. (智能体联盟 (OpenLOA)：一个可扩展的编排框架，用于通过模块化工具和自定义界面创建个性化 AI 智能体。)

Automatically generate high-quality company research reports.

25+ skills for AI coding assistants — multi-agent panels, evaluation pipelines, testing, browser automation, and more

Modern Asana CLI, built with AI agents in mind

Multi-agent governance for Claude Code. Council deliberates, votes, dispatches, enforces quality gates.

Budget-aware context compilation and context firewall for tool-heavy AI agents.

Platform-agnostic project management system for seamless collaboration between humans and AI agents. Features: Kanban board, REST API, adaptive UI, zero-config agent integration.

🤖 Build and explore powerful AI agents that solve real-world tasks using tools, memory, and reasoning within a collaborative hub.

Pocket Flow: A minimalist LLM framework. Let Agents build Agents!

AutoTask: a novel LLM framework to execute user commands by exploring and learning from mobile GUI.

Official implementation of the paper "GazeInterpreter: Parsing Eye Gaze to Generate Eye-Body-Coordinated Narrations" (AAAI 2026)

LLM-based agent for in-depth photo/image manipulation

A Model Context Protocol (MCP) server that enables LLM clients to interact with macOS applications through AppleScript. Built using the @beyondbetter/bb-mcp-server library, this server provides safe, controlled execution of predefined scripts with optional support for arbitrary script execution.

SearchSynth fetches and summarizes web search results using SerpApi and Groq for insightful analysis.

Official Python SDK for FoxNose

A text editor for LLMs, not humans.

LLMs to take action and execute the actions.

Personal Discord server code agent for Claude/Codex/Gemini

An experimental LLM Agent to build integrations for you.

两个文件实现的轻量化浏览器 agent。简单、开源、基于 Playwright

A python package for extracting composition-property data from scientific articles for building databases

CSR-Bench: Benchmarking LLM Agents in Deployment of Computer Science Research Repositories

Build LLM ReAct Agent framework from scratch in Python

A curated survey of Trustworthy Computer-Use Agents (CUA): trust boundaries, formal analysis, evaluation gaps, and governance — with a structured, per-section reading list of papers.

Outline-Driven Development for Gemini CLI - methodology + skills + agents for Google Gemini coding workflows.

LOAB: A benchmark for evaluating LLM agents on end-to-end mortgage lending operations under real regulatory constraints.

Sustainable Hydroponic domain-specific LLM developed to improve sustainable farming.

The platform features: Provide 24/7, personalized guidance on policy selection and claims via voice or chat. Ensure clear understanding of policy terms. Automate form-filling with Al for error-free applications and higher claim acceptance rates.

Enables users to interact with the LLM via Ollama by implementating a client-server architecture utilizing FastAPI as server-side framework and Streamlit for user interface.

An open-source AI agent platform that does the work for you.

Claw Orchestrator

Polymorphic Agent Swarm Architecture: model-agnostic, self-organizing multi-agent system with 6 topologies, 1,095+ tests (adversarial, chaos, e2e, integration, performance, MCP, Ray), 18 completed phases.

Multi-agent pursuit in matrix world (pursuitMW)

This project uses UVM to verify an SPI Slave connected to internal RAM. It includes multiple agents (active and passive) and integrates assertion-based verification for both SPI and RAM behavior.

AI Agent Orchestration Engine — spawn and command an army of AI agents with Roman military precision

Interactive setup wizard that generates project-specific CLAUDE.md configuration files for Claude Code integration. Supports 12 app types, 7 development methodologies, and 19 feature sets.

Materiales de la charla "Agentes inteligentes"

This is the Official Implementation of "CANTANTE: Optimizing Agentic Systems via Contrastive Credit Attribution" by Tom Zehle

autodev 是一个自动化开发流程编排工具。它通过 plan -> dev -> review -> arbitrator -> merge 的闭环循环，驱动多代理协作，直到任务通过质量门禁并完成合并。

About Most AI systems forget. MultiHead organizes a team of specialists that don’t. MultiHead is a system for breaking down complex tasks, executing them across specialized AI components, verifying results, and building persistent knowledge over time.

Machine Learning and Guidance of Swarm in Dynamic and Partially Observable Environments

AI-powered novel writing system with dual-system support (male/female-oriented), framework agents, and multi-dimensional quality evaluation.

multi-agent AI framework for VScode copilot with semantic memory and gemini-CLI baked in

Orchestration MCP for Claude Code

Ipsa cognitio fructus

Real-time global intelligence platform — OSINT monitoring + multi-agent predictive simulation in Gleam/OTP

Docker Compose for AI agents. Define your agent team in YAML, run them with one command.

Stealth Temple: Game with Multi-Agent, Behaviour-oriented Enemy Artificial Intelligence (Bachelor Thesis)

Growny helps users manage tasks, notes, and reminders using natural language. It leverages AI and vector databases for smart organization and fast retrieval, making productivity simple and efficient.

"unitmux" — Unifies your AI coding sessions into a single floating interface.

YAML-driven CLI to design, validate, and generate multi-agent team configs from a single manifest

Distributed Agent Knowledge Base - Multi-agent collaboration system for Claude Code

A general pytorch implementation of the Minimax Multi-Agent Deep Deterministic Policy Gradient (M3DDPG) algorithm used for multiagent reinforcement learning.

Personal AI assistant gateway powered by Claude Code — multi-agent, multi-channel (Discord/Telegram/TUI), session management, tool approval, memory system

The next-generation sovereign AI ecosystem. Mnemosyne Neural OS empowers users with multi-model agents, local-first data privacy, and an encrypted knowledge vault. Experience the future of private, autonomous edge-to-cloud R&D.

Advanced lecture of MIT 16.412 - Cognitive Robotics - in Spring 2019

I want to speak to the manager

Automated LLM red-teaming system with 4 AI agents

Multi-Robot Path Planning

Multi-expert roundtable discussion powered by Resonnet.

Local AI mesh — multiple agents, shared persistent memory, real-time dashboard, browser automation. Runs on your hardware.

Capability-based compiler/runner for reproducible agent scenarios

Autonomous AI trading system using xAI Grok for market analysis and Interactive Brokers for execution

An autonomous self-driving agent for slowroads.io using OpenCV, DBSCAN, RANSAC, and a PID controller

self made agent what have bunch of tools can create files, folders, can analyze, pylint, autopep8, Difff, Edit and Apply , SummerizeWebage, TavilyWebserach uvm.

A structured execution protocol for echoes in AI systems. It includes a series of echoes designed to optimize, evaluate, and plan processes in conversational AI

express.js styled agent orchestration Library for typescript community

The AI Toolkit for Go.

PROMPT™ is a human-first prompt framework for people who hate generic AI answers. It’s built from real, geeky metadata work and years of practicing structured inquiry with humans—so AI stays in context and doesn’t waste your time. On the backend, it's a powerful, versatile a structured interaction schema for AI agents, LLMs, and agentic workflows.

Natuleadan's AIO for AI agents fullstack NextJS Supabase Uptash (and more) with dynamic SSR pages and RBAC dashboard for administration with cooked APIs for use and connect agents with tooling

An Inference Operating System that reduces unnecessary LLM calls by structuring intelligence before scaling it.

This agent intelligently analyzes your shopping intent and searches across 24 connected Shopify stores in parallel. Using a coordinated multi-agent system, it discovers and show the most relevant products,product infos and prices.

A context-building execution engine for AI-native programming

🐆 Self-hosted AI workstation stack for @amd

Multimodal AI: How Machines Learn to See, Hear, and Understand Together

Multi-agent intelligent irrigation system using Google Gemini ADK. Proactive plant care with explainable AI decisions, real-time monitoring, and automated watering control.

GO-CODE is a terminal-based AI coding agent. It helps you automate coding tasks, execute shell commands, and manage files directly from your terminal. GO-CODE is designed for developers who want to interact with their codebase and operating system efficiently using natural language.