Custom agents

Code for implementing/applying ODM*, PPO, MAAC, IC3Net and PRIMAL (PPO version) on a Multi-Agent gridworld environment.

PyTorch Official Implementation of CoRL 2023 Paper: Neural Graph Control Barrier Functions Guided Distributed Collision-avoidance Multi-agent Control

A comprehensive framework for benchmarking single and multi-agent systems across a wide range of tasks—evaluating performance, accuracy, and efficiency with built-in visualization and tool integration.

(: SMILE! The positive prompt language for structured prompt engineering — used for complex prompts, multi-turn pipelines, agentic engineering. Modular & maintainable prompts for powerful Large Language Model responses.

This repository is a paper digest of multi-agent behavior (motion / trajectory) prediction (forecasting / generation).

this is a simple "chrome" browser web page automated testing tools. It is based on "Chrome DevTools Protocol" authoring and provides a set of standard and friendly EPL calling interface.

a novel framework for stock portfolio trading that employs a 'Relaxation and Refinement' strategy to boost the Soft Actor-Critic (SAC) agent

GitHub Copilot — AI pair programmer with chat, code suggestions, PR summaries, and CLI support.

Microsoft Office 2024 — Word, Excel, PowerPoint, Outlook, OneNote with cloud collaboration and AI-powered Copilot features.

Annoucing Instructor Cloud

Clawforce is the infrastructure for deploying persistent, proactive agent workforces that execute complex workflows, collaborate as teams, and deliver real outcomes — without constant human supervision.

The Okta MCP Server is a groundbreaking tool built by the team at Fctr that enables AI models to interact directly with your Okta environment using the Model Context Protocol (MCP). Built specifically for IAM engineers, security teams, and Okta administrators, it implements the MCP specification to help work with Okta enitities

Agent驱动的实时广播电台 实验性项目

AI Chatbot in HTML CSS & JavaScript

Kumpulan data yang akan digunakan untuk keperluan chatbot bahasa Indonesia dengan kode chatbot sederhana menggunakan Typescript

LLM-Blender: Ensembling framework that maximizes LLM performance via pairwise ranking. Employs PairRanker to rank candidates and GenFuser to merge outputs, generating superior responses by combining the diverse strengths of multiple open-source models.

Service to import data from various sources and index it in AI Search. Increases data relevance and reduces final size by 90%+. Useful for RAG scenarios with LLM. Hosted in Azure with serverless architecture.

Local-first RAG desktop app & official MCP Server. Let any AI instantly search your private Markdown, PDF, and 1290+ document formats. (本地优先的 RAG 桌面端与官方 MCP 服务器。让任意 AI 瞬间检索你的私有 Markdown、PDF 及 1290+ 种文档格式。)

Foundation is a flexible, modular, and composable framework to model socio-economic behaviors and dynamics with both agents and governments. This framework can be used in conjunction with reinforcement learning to learn optimal economic policies, as done by the AI Economist (https://www.einstein.ai/the-ai-economist).

This repository shows you how to build real-time, voice-enabled AI agents with Pipecat and Amazon Bedrock

An MCP server for AI agents to automate token swaps on Uniswap DEX across multiple blockchains.

🌸 Local, Open Source AI agent/App Builder that lives inside your Next.js app

User profile and long-term memory for your AI agent. Drop-in LLM proxy that gives AI model persistent memory and structured user understanding.

Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments (EMNLP'2024)

A simple way to write multi agents systems

A powerful task-oriented dialogue agent that can collect information through structured conversations. It supports dynamic field validation, multi-field information extraction, and state management.

Multi-Agent Deep Reinforcement Learning by using Asynchronous & Impala Proximal Policy Optimization in Pytorch with some explanation

（AAAI 2025）MUSES: 3D-Controllable Image Generation via Multi-Modal Agent Collaboration

RobotFramework-AI is a library that adds AI functionality to the Robot Framework. It can generate test data for you using the RealTestDataGenerator but also reply to your messages with the Chatbot.

Get your favorite AI Chat websites in the sidebar of your Windows OS similar to Windows Copilot but also adds ChatGPT, Bard, You and Bing Chat.

A Laravel and React JS SPA created through heavy utilization of AI (ChatGPT and Copilot).

An MCP Server to utilize Codelogic's rich software dependency data in your AI programming assistant.

A Golang autonomous AI agent framework for assisting real work

Tocket: a file based project notebook that many AI agents read and write together

Neural Interactive Responsive Agent (N.I.R.A)

A sample Implementation of agent bot APIs in chatwoot using rasa

Source code for the gopher Slack Bot rewrite

An Self learning AI Chatbot who doesnt let you waste food by recommending awesome Recipies

Reference Implementations for the RAG bootcamp

Convert Files / Folders / GitHub Repos Into AI / LLM-ready Files

Agent Canvas helps teams describe, prototype, evaluate, and export multi-agent systems that run on the Microsoft Agent Framework. Start from a Lovable-inspired landing page, prompt an initial design, refine it on the canvas, and ship a paired FastAPI backend + React frontend deliverable.

An open-source AI voice agent platform that turns conversations into 100% accurate, user-verified data via a visual form.

Efficient multi-agent task automation and management system.

Official repository of the paper "FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning"

Code for "Context-aware Communication for Multi-agent Reinforcement Learning"

Persistent memory and cognition for AI characters on local LLMs. Global-workspace attention, appraisal codelets, episodic reconsolidation, metacognition.

A categorized list of ai services for Developers.

A directory of practical and usable AI agents resources from applications and platforms to frameworks and utilities and other parts of the growing ecosystem

An implementation of an Autonomous Vehicle Agent in CARLA simulator, using TF-Agents

TARS is a centralized hub for discovering, creating, editing, and managing Claude Code resources. It provides a visual interface for managing skills, agents, commands, hooks, MCP servers, and plugins across multiple projects with safe apply/rollback operations and profile-based configuration sharing.

Experimental framework for ECS based AI agent simulations

Glupe 🙏🌹. Constrain where AI can generate code. Keep the rest of your codebase untouched.

[ACL'26 Main Conference] Retrieval as Generation: A Unified Framework with Self-Triggered Information Planning

Official Implementation of RSS2025 Paper: Songyuan Zhang*, Oswin So*, Mitchell Black, Zachary Serlin, Chuchu Fan: "Solving Multi-Agent Safe Optimal Control with Distributed Epigraph Form MARL".

Auto AGENTS.md Generator for Git - Automatically creates starter AGENTS.md (with CLAUDE.md symlink) when cloning empty repositories

CLI for Monarch Money - access your financial data from the command line. Built for agents(claude code) and humans.

Three.js + Torch implementation of Unity's ML-Agents framework for agent training and visualization in browser

A hands-on lab to get started with AI Native Development with GitHub Copilot

Content Operating System — content marketing, SEO, social media, publishing. Create it. Publish it. Measure it. Optimize it.

Uses an AI agent (powered by Google Gemini via the Agno framework) to intelligently propose and execute a plan for organizing files within a specified directory on your computer.

yoink is an AI agent that removes complex dependencies by reimplementing only what you need.

Let agents perceive, indicate, and act in any application.

A free 3D Printing MCP server that allows for getting live printer state, webcam snapshots, and printer control.

Stream LLM output (ChatGPT, Claude, Gemini) into Flutter as live markdown with typewriter and fade reveal, LaTeX, RTL and pause/skip control.

Bot that hosts mafia games in Telegram's groups and supergroups

SPY put-credit validation and real-money control plane with broker-backed ledgers, deterministic risk gates, hybrid RAG, reconciliation, and $1k/mo after-tax evidence tracking.

A high-performance, local, offline-first AI memory system built in Rust

Evaluating Safety of Autonomous Agents in Mobile Device Control (AAAI 2026 AI Alignment Track)

The official repository for "CartoAgent: a multimodal large language model-powered multi-agent cartographic framework for map style transfer and evaluation".

Automatic support for (Claude) Skills for any coding agent that supports AGENTS.md

Argus Automation — SOTA desktop automation for AI agents. Works with Claude Code, Codex, and OpenClaw.

Local embeddings, semantic search, classification, reranking, chat, speech to text, summarization, translation and image search for C#, Go, Rust, Python, C++ and the command line.

(Mostly) autonomous AI coding toolkit for Claude Code based on RALPH and PRD-driven development.

AI Appliance Builder — YAML-defined AI agents and workflows. Ship as Docker, Kubernetes, ISO, or standalone binary.

Phone notifications when Claude Code or other agents needs attention on remote servers or your local laptop

A platform for Interactive AI-assisted Hypothesis Generation [ACL 2025]

Community-driven Claude Code marketplace with specialized AI agents for the full SDLC. Features multi-agent coordination, workflow orchestration, and 100+ API integrations. Includes code review, security scanning, deployment automation, performance optimization, and more. Production-ready tools built by developers, for developers.

Browser-as-infrastructure for AI agents. Isolated Chrome sessions with fingerprint controls, network isolation, and full control via REST API / CLI / Web UI.

Deterministic multi-agent pipeline for end-to-end software development, orchestrating CLI-based AI tools (e.g. Gemini, Claude, Codex) through tmux-controlled sessions.

Your personal multi-asset quant research team, powered by LLMs. Crypto + A-share + HK + US, with backtest engine, factor lab and event-driven news intake.

50+ AI agents that audit codebases for security, architecture, testing and documentation issues

No viewers? No problem! Use AI Viewers

The highest-scoring AI memory system ever benchmarked that isn't reliant on LLM reranking. And it's free & burns less tokens.

FAT Agent (Fix, Audit, Test) — a Claude Skill that automates post-launch website QA. Audits SEO, security, accessibility, performance, and more.

SPEC-first multi-agent framework for Claude Code.

Structured AI agent orchestration - manage agents like a real team. Open source, self-hosted, MIT licensed.

Security-first package manager for AI agent skills

Agent Identity Protocol - Zero-trust security layer for AI agents. Policy enforcement proxy for MCP with Human-in-the-Loop approval, DLP scanning, and audit logging.

Self-hosted intent radar — Reverse RAG for any input stream.

🦀 A high-performance code agent written in Rust, combining the best features of WCGW for maximum efficiency and semantic capabilities.

Multi-Agent System built with Google ADK and OpenRouter models, coordinating specialist agents to query PostgreSQL (via MCP Toolbox) and Data Commons for HDB resale data and global statistics.

Claude/Agent Skills for DigitalOcean App Platform - deployment, migration, networking, database configuration, and troubleshooting

Capability-layer harness: mobile-first AI agent framework — an OpenClaw alternative that lives on your phone.

Open Source WhatsApp Business API Gateway — Multi-engine, Self-hosted, Enterprise-ready

基于 LLM agent 的党政机关公文自动排版工具

BMAD Method Framework for Agent Zero

A Claude Skill that orchestrates multiple LLMs as a council, generating collective intelligence through peer review and chairman synthesis

WeChat iLink Bot API Go SDK - 微信官方机器人启动框架