Custom agents

Learning to Ground Multi-Agent Communication with Autoencoders [NeurIPS 2021]

A basic voice agent built with Python agents framework

Tray icon tool for the MeshCentral Agent. It displays the state of the agent, you can start and stop the agent and request help.

Copytrading Agent on Hyperliquid

Projeto desenvolvido durante o NLW Agents da Rocketseat

Marzban superset for managing multiple panels and agents

[ICCV 2025] Preacher: Paper-to-Video Agentic System

Natural language test scenario runner agent with MCP tools

An MCP project that supports multiple agents chatting and collaborating with each other.

A java agent for tracing which can be configured via simple text file and instruments the code without rebuilding the project.

Unity project showcasing A* pathfinding, fully jobified & burst compiled. It also contains examples of RaycastCommand and BoxcastCommand that are used to build the grid, as well as another example of the usage of IJobParallelForTransform, used to move the agents.

Cognitive engine for AI agents — semantic memory, observations, embeddings, dream consolidation. Cloud Run service + MCP tools.

This repository contains the Matlab source codes (to use in Robotarium platform) of various rendezvous controllers for consensus control in a multi-agent / multi-robot system.

Record your workflow once, run it on autopilot forever with an AI agent.

Stop paying for AI APIs during development. LocalCloud runs everything locally - GPT-level models, databases, all free.

A minimal implementation of GraphRAG, designed to quickly prototype whether you're able to get good sense-making out of a large dataset with creation of a knowledge graph.

Course on solving heterogenous agent models

AgentX - Agent Extension: MCP Servers, Agent Skills and Plugins Manager

Ready-to-use agent that can interact directly with any tool or native endpoint, in less than 5 lines of code

Agen is a minimalist language for agent loops and state machines.

oSIP is a LGPL implementation of SIP. It's stable, portable, flexible and compliant! -may be more-! It is used mostly with eXosip2 stack (GPL) which provides simpler API for User-Agent implementation.

A browser built on top of a community-driven registry of tools and configurations for fast, low-cost browser automation by and for agents

WebResearcher: An Iterative Deep-Research Agent，迭代式深度研究智能体

RL2Grid is a standardized benchmark for reinforcement learning (RL) agents in realistic power grid environments. Built on top of Grid2Op, it models real-time operations such as topology optimization and redispatching, with full AC power flow simulation, stochastic events, expert-informed heuristics, and safety-critical constraints.

Source code for the IBM Granite AI Model Workshop

This is the official code base of AgentNetTool in OpenCUA. Website: https://opencua.xlang.ai/

Adds nodes to n8n for interacting with AI agents using Google's New Agent2Agent (A2A) protocol. Send tasks, manage interactions, and process results from A2A-compatible agents within your workflows

Most WhatsApp gateways stop at "send a message." **NOXUS AI Open WhatsApp** goes further: it ships a **grounded AI agent** that answers customers from your own knowledge — and can call your live APIs by slash command before replying. You bring the data and the APIs. NOXUS does the WhatsApp, the AI, and the operations console.

File-based context resolution for AI agent DAG workflows. Three primitives, zero dependencies.

Meta-specification framework for AI Agents to generate Spec-driven X toolkits automatically.

CS294/194-196 Large Language Model Agents

A browser-based UI for Claude Code — chat, run workflows, manage MCP servers, track costs, and orchestrate autonomous agents from a local web interface. Installable as a PWA.

Background coding agent — polls Linear, runs DOT graph workflows, ships PRs

[AAAI 2026] Benchmarking Language Model Agents in Algorithm Search for Combinatorial Optimization

Digital Agents Meet World Models: A Survey

Outcome-based persistent memory MCP server for Claude Code and OpenCode. Good advice promoted, bad advice demoted. pip install roampal.

xiaozhi AI

In this tutorial we will learn how to create a powerful AI chatbot using LangGraph, FastAPI, and Streamlit.Learn to define a FastAPI backend endpoint for processing requests, integrate LangGraph agents with dynamic model selection, and design an intuitive Streamlit UI for seamless user interaction.

Advanced agent skills for real-time web intelligence. Features specialized focus modes, AI-powered answer synthesis, parallel search, and smart filtering. Built on the Agent Skills open standard.

The Generative AI Toolkit is a lightweight library for building, testing and evaluating AI agents in Python, using any of the LLMs supported by the Amazon Bedrock Converse API.

A Model Context Protocol (MCP) server providing TomTom's location services, search, routing, and traffic data to AI agents.

CLI tool for Turkish legislation (mevzuat.gov.tr). Designed for AI agents and programmatic use.

MCP-native collaboration server for AI agent teams — real-time messaging, task management, and web dashboard with just 1 npm dependency

[ICLR 2026] SR-Scientist: Scientific Equation Discovery With Agentic AI

Decentralized policy network for time-optimal multi-drone flight using multi-agent reinforcement learning.

Neuro-Symbolic Agentic Protocol

A collection of agentic iOS/watchOS audit skills and playbooks for IDE agents and CLI tools. Extracted from the development of Haptix.

Automated black-box REST API testing using graph-based modeling, LLMs, and multi-agent reinforcement learning.

A plugin with compound engineering workflows and memory for AI coding agents

Dragon Brain — persistent long-term memory for AI agents via MCP (Model Context Protocol). Knowledge graph (FalkorDB) + vector search (Qdrant) + CUDA GPU embeddings. Works with Claude, Gemini CLI, Cursor, Windsurf, VS Code Copilot. 30 tools, 1121 tests.

Market Map agent eval suite for the Reforge AI Evaluation course

RLM agent harness - built on Deep Agents

Command Augmentation support for BOFs and .NET assemblies across agents

用 ~5000 行 Python 还原 CC 的核心 Agent Runtime。

Skill to control an Android device with an agent

Your coding agent spends 90% of its tokens finding code, not writing it. Reduce your token usage by 50x with CodeDrift !

A compact operating covenant for AI agents.

A comprehensive benchmarking framework for evaluating and optimizing CPU-centric agentic AI systems across multiple workloads, reproducing results from the research paper: "A CPU-Centric Perspective on Agentic AI"

From idea to shipped product: high-quality engineering workflows for AI agents.

Sandboxed AI agents, reachable from anywhere

A unified, AI agent-friendly SDK for the Unitree Go2W quadruped robot that enables seamless integration of perception, planning, and control through a single API interface.

Fast Delphi/Pascal symbol search for AI coding agents - Now includes Delphi LSP

Agent Trending是一个聚焦 AI Agent 的开源研究项目，系统整理了 2025.01—2026.03 期间 8701 篇学术论文，围绕 15 个核心方向完成分类、去重、标注与趋势分析。项目包含月度论文索引、细分方向论文集、15 份技术趋势报告，以及 1 份全局趋势总报告和 1 份下一代 Agent 原型设计文档，适合研究者、工程团队和产业决策者快速把握 AI Agent 的技术演进与落地脉络。

[AAAI 2026 Oral] Automatic Multi-agent Communication Topology Design

PiFlow: Principle-aware Scientific Discovery with Multi-Agent Collaboration

pi-coding-agent docker compose

A one-click installer that scaffolds a complete GitHub Copilot agentic coding environment into any project

[ACL26 Findings] LiCoMemory: Lightweight and Cognitive Agentic Memory for Efficient Long-Term Reasoning

A collection of Agent Skills for building AI-powered apps with Replicate

Turn Claude Code into a full dev team — 13 AI agents, documentation-first pipeline, TDD enforcement

SAFi is an open-source runtime governance engine for agentic AI that enforces your policies, governs agent actions, and records every decision for audit.

《深入Claude Code》- 基于源码的AI Agent架构设计与工程实践完整指南 (14章)

[NeurIPS'25] ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptions

This project implements a comprehensive framework for Knowledge Graph Retrieval Augmented Generation (KG-RAG). It focuses on financial data from SEC 10-Q filings and explores how knowledge graphs can improve information retrieval and question answering compared to baseline approaches.

Privacy-first semantic code navigation MCP server using RAG. Features deep AST multi-language support (Go, PHP/Laravel/WP, JS/TS/React, Python), 100% local LLMs (Ollama), and vector search (Qdrant) for AI IDEs like Cursor, Windsurf, Copilot, and Claude.

An experimental autonomous research system that conducts comprehensive, multi-hour research sessions and produces book-length reports with full citations on any topic.

Home Assistant custom integration — Mistral AI as conversation agent and Voxtral as speech-to-text engine. ⚠️ Please note this is not an officially supported integration and is not affiliated with Mistral AI in any way.

小红书 AI 自动发帖Agent —— 用 Codong 语言构建

Spore Agent——更加友好的人机交互Agent。Spore Agent — An AI agent built for better human interaction.

面向 AI Agent 入门者的教学项目。通过一个完整的电商客服 Agent，让你亲眼看到每一轮对话中 Agent 内部经历了哪些环节、做了什么决策、调用了什么工具、生成了什么 Prompt。

Multi-agent AI trading system using LLM-powered analyst agents (Buffett, Munger, Burry, etc.) with free data sources (SEC EDGAR + yfinance) and Alpaca integration.

Official Repo: AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery

Enforce Architecture Decision Records as executable rules — for both humans and AI agents

A token-efficient open-source AI assistant that remembers, adapts, and improves — secured, self-hosted, and entirely yours.

Extract Google Maps business leads and enrich contact details using AI & web scraping

Distributed issue tracking embedded in Git — track issues locally, sync anywhere, no server required

Open-source SvelteKit + Convex SaaS template that gets harder to break the more agents work on it. Auth, billing, admin, AI chat, email, and i18n ship end to end. Every recurring bug class becomes an ESLint rule, banned-pattern check, test, or validator, enforced in CI. Deploy on Cloudflare or Vercel for $0.

29 AI agent skills for marketing tasks, built for Claude Code and similar AI coding assistants

The benchmark tasks and evaluation harness for "PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments".

OpenCode integration plugin for Hermes Agent — dispatch coding tasks to OMO's multi-agent harness

Disease Mechanisms KB

An open-source Android AI voice assistant built with Kotlin, Jetpack Compose, and on-device ML (BERT + TFLite, MediaPipe, ML Kit).

10 AI agent skills for Claude Code — waterfall email enrichment, TAM building, signal discovery, job change detection, and outbound automation. Powered by Deepline CLI with 28+ GTM data providers.

Agent skill for deepfake detection & media safety — detect AI-generated audio, images, and video with Resemble AI

专利侵权分析系统 —— 输入专利公开号，产出竞品侵权分析报告；同时打包成 skill，可被任意 agent（codex，claude code 等） 调用。

AI Agent trend judgment with multi-observer sources, emerging-project discovery, scoring rationale, weekly decisions, and tool fallback.