C++ agents

Engineering LaCAM*: Towards Real-Time, Large-Scale, and Near-Optimal Multi-Agent Pathfinding (AAMAS-24)

Algorithm for prioritized multi-agent path finding (MAPF) in grid-worlds. Moves into arbitrary directions are allowed (each agent is allowed to follow any-angle path on the grid). Timeline is continuous, i.e. action durations are not explicitly discretized into timesteps. Different agents' size and moving speed are supported. Planning is carried out in (x, y, \theta) configuration space, i.e. agents' orientation are taken into account.

Lightweight C++ LLM agent framework

ICRA 2024 | Decentralized Multi-Agent Trajectory Planning in Dynamic Environments with Spatiotemporal Occupancy Grid Maps

Lightweight UE5 plugin that exposes Unreal Engine's reflection system over TCP+JSON — let AI agents call UFunctions, read/write UProperties, and inspect any UObject in a running editor, zero engine modification required.

MAPF-LNS2: Fast Repairing for Multi-Agent Path Finding via Large Neighborhood Search

Priority Inheritance with Backtracking for Iterative Multi-agent Path Finding (AIJ-22)

Heterogeneous Containerization of Agents

WinDbg Copilot - Agentic Debugging extension

A Repository with C++ implementations of Reinforcement Learning Algorithms (Pytorch)

Fork of x library for collaborative decentralized visual-inertial odometry

Open Source Implementation of Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution

BCP-MAPF – branch-and-cut-and-price for multi-agent path finding

A pre-LLM agent that plays the 3rd gen Pokemon games

"Multi-robot Coordination with Agent-Server Architecture for Autonomous Navigation in Partially Unknown Environments", IROS 2020

simple multi-agent pathfinding (MAPF) visualizer for research usage

A high performance C++ SDK for AI Agents

Akonadi resource agent for Microsoft Exchange using Exchange Web Services (EWS) protocol

SNMP Agent built with Arduino

Zabbix agent for Arduino

Conflict-based search for multi-agent path finding (MAPF)

Open source endpoint agent providing host information to Zeek. [v2]

Snake playing agents

Pandora is an Agent-Based Modelling framework for large-scale simulations

Modular Agent Based Evolution Framework

Demonstrate calling a kernel function and handle process creation callback against HVCI

Online multi-agent trajectory planner using linear safe corridor (LSC)

A large collection of mostly reinforcement learning agents.

a simple tool for easyily dev/debug using frida and write module for agent. (mainly used for android)

ROCmFPX Family for AMD Hardware and Processors. More quants and special agent quants

Daily Leetcode masterclass with Claude code DSA mentor

GPT2⚡NCNN⚡中文对话⚡x86⚡Android

A cross-platform AI agent orchestrator in C++ that turns any device — including your phone — into a self-contained, multi-agent automation platform

Improved Heuristics for Multi-Agent Path Finding with Conflict-Based Search

LaCAM: Search-Based Algorithm for Quick Multi-Agent Pathfinding (AAAI-23)

A high performance C++ SDK for AI Agents

[CVPR 2025] MAC-Ego3D: Multi-Agent Gaussian Consensus for Real-Time Collaborative Ego-Motion and Photorealistic 3D Reconstruction

Xplor (Formerly know as Xplorer) an AI-native Chromium fork with Grok built in at the source level: Grok as the default search, the "Grok it" page button, a unified Grok toolbar (X Chat · Grok Build · Grok Web · Groki), Grok Build apps, and an always-on local agent gateway (CDP + high-level API) for any agent to drive.

Online deadlock-free multi-agent trajectory planner using linear safe corridor (LSC)

Anytime Multi-Agent Path Finding via Large-Neighborhood Search

openJiuwen agent-protocol provides implementations of agent communication protocols, including C++ SDKs for MCP and A2A protocols.

API Framework heavily relying on the power of DuckDB and DuckDB extensions. Ready to build performant and cost-efficient APIs on top of BigQuery or Snowflake for AI Agents and Data Apps

GenDB, an LLM-Powered Generative Query Engine Built for the Future

Repository for predictive dual-arm reactive motion planning

GPU-accelerated, multi-GPU simulator for large-scale network flow and agent-based optimization: powers ICML 2026 deep-RL dispatch, MoE routing policies, and closed-loop LLM-driven fleet optimization over networks with hundreds of thousands of nodes and millions of agents.

A blazing-fast CLI tool to export a directory's structure and contents into a neatly formatted `.txt` or `.json` file.

Python bindings for llama.cpp

Cross-Platform High-Level LLM Library

Additive Groves, Bagged Trees with Feature Evaluation, Interaction Detection, Visualization of Feature Effects.

[AAAI-2024] Follower: This study addresses the challenging problem of decentralized lifelong multi-agent pathfinding. The proposed Follower approach utilizes a combination of a planning algorithm for constructing a long-term plan and reinforcement learning for resolving local conflicts.

SMART is an efficient soft-tool that bridge the gap between Multi-Agent Path Finding (MAPF) and real-world application. More details can be found in our paper: Advancing MAPF towards the Real World: A Scalable Multi-Agent Realistic Testbed (SMART) [1].

Multi-Agent eXchange simulator developed at Oxford-Man Institute

AI-powered ESP32 pentesting device with RF replay, RF jammer, IR control and BadUSB capabilities. Built for LilyGO T-Embed CC1101 & LilyGO T-Watch-S3

redis-llm integrates LLM with Redis. It can help LLM to access private data, and remember long chat history.

instinct.cpp provides ready to use alternatives to OpenAI Assistant API and built-in utilities for developing AI Agent applications (RAG, Chatbot, Code interpreter) powered by language models. Call it langchain.cpp if you like.

Faiss-based library for efficient similarity search

🐬 A pink qFlipper fork with LOTEI — a 100% local AI dolphin (Ollama) that chats, talks, watches your Flipper's screen, and one-click-installs custom firmware.

A multi-room chat application in C++ using Winsock. Supports real-time messaging, private chats, undo/redo, history, and search. Built with threads, mutexes, and socket programming for concurrent multi-client communication.

A toolkit for painting agent-based mesoscale molecular simulations and illustrations.

Semantic retrieval for AI agents: high-recall memory and code search that cuts coding-agent token usage by nearly 50%

A wrapper class to hide the original calling address of a function

Vector Database with support for late interaction and token level embeddings.

Native C++ AI assistant module for the Godot 4.7 editor - multi-provider LLM chat, GDScript code generation & execution, scene-aware context, on-demand API docs and gotchas injection

Environment Generator for Air Learning Project. This version is build on top of UE4 game engine

Code for "Joint Policy Search for Collaborative Multi-agent Incomplete Information Games"

Strata Studio is an agentic DAW that your AI agent (Claude Code, Cursor, Codex) can natively control so you can focus purely on making music.

重生之我是 AI 打工人。前世，我的身份默默无闻，来去匆匆，不知道自己将在何地出生。然而，命运给予了我难得的机会，让我重生为一名 AI 打工人。

Agent Based Class Design

Anthropic’s Model Context Protocol implementation for Oat++

C++17 port of librosa with wasm and SPM package. Done with agents. YMMV.

Sliver agent rewritten in C++

This repository contains the SDK that DLP agents may use to become service providers for the Google Chrome Content Analysis Connector.

🤖💬 Arduino library for integrating AI chat like OpenAI's ChatGPT, Hugging Face Transformers, and more.

Robotics-Deep Reinforcement Learning Project: Deep RL Arm Manipulation by using DQN (Deep Q-Learning Network) agent simulated on ROS-Gazebo with C++ API.

Agent-first semantic data infrastructure: durable, queryable memory and document understanding for AI agents. Hybrid retrieval (P-HNSW vector + BM25 full-text), cross-namespace semantic query, SPC ingestion pipeline, MCP server & Python SDK. AGPL-3.0.

The complete AI platform on a $3 microcontroller. Sub-millisecond inference. Zero hallucinations.

基于OPENAI辅助UE开发，接入openai-api，使用DALL.E自动生成模型，Chat-GPT自动设计蓝图.

Concrete Multi-Agent Path Planning Enabling Kinodynamically Aggressive Maneuvers (npj Robotics 2026)

一款即时通讯软件 | 🎇 仿 QQ NT | 🎇 基于ElaWidgetTool仿fluent ui框架 | 🎇 Linux后端及可跨平台客户端 |

macchina.io REMOTE provides secure remote access via web (HTTP), shell (SSH), remote desktop (VNC, RDP) and other protocols to IoT devices behind routers or firewalls. No port forwarding, scarce public IPv4 addresses, or complex and inflexible VPNs required. This SDK contains the Device Agent and client tools.

SpecialAgent is an Unreal Engine 5 plugin that implements a Model Context Protocol (MCP) server, allowing Large Language Models like Claude to programmatically interact with UE5 projects. With 71+ tool endpoints across 14 service categories, LLMs gain comprehensive control for building complex 3D environments.

NVIDIA Halos Outside-In Safety Blueprint extends robot perception beyond on-board sensors by using external infrastructure cameras and AI agents to dynamically control robot behavior and perform at maximum efficiency.

A framework for building intelligent agents

The best open source user intent based chatbot framework

ESP32 Arduino Framework Library to allow connection to OpenAI Chat Completions Endpoint

基于各种LLM的聊天机器人框架，支持多语言，语音唤醒,语音对话,本地执行功能,支持 OpenAI，Grok, Claude，讯飞星火，Stable Diffusion，ChatGLM，通义千问，腾讯混元，360 智脑，百川 AI，火山方舟，Ollama ,Gemini等API

Your private AI companion that lives on your wrist. Complete local AI assistant with emotional intelligence.

A modular Telegram bot framework for C++ developers.

ns3-gym for multi-agent

Priority Inheritance with Backtracking for Iterative Multi-agent Path Finding (IJCAI-19)

A Fleet of Unitree GOs (GO1 and GO2) capable of Heterogeneous Collaborative Exploration.

Graph Attention-Guided Search for Dense Multi-Agent Pathfinding (AAAI-26)

使用AI Agent创造ICPC风格的题目

The HiPIMS-FLAMEGPU Coupled Model Framework integrates the high-performance hydrodynamic modeling capabilities of HiPIMS with the flexible agent-based modeling environment of FLAMEGPU. This combined framework allows for the simulation of complex interactions between human activities and flooding processes.

Decentralized Multi-Agent Exploration on ROS with Distributed Deep Reinforcement Learning using A3C Algorithm

Improving LaCAM for Scalable Eventually Optimal Multi-Agent Pathfinding (IJCAI-23)

Behavior planners based on single- and multi-agent Monte Carlo Tree Search

This is an umbrella repository that contains links and information about all the tools and algorithms related to the POGEMA Benchmark.

AI浏览器 MCP Server — Windows 本地浏览器自动化 | 243 工具 | Cursor/Claude/Cline | Web Scraping · JS逆向 · CDP断点 · 指纹伪装 · 填表RPA | FBrowser CEF 内核 | MIT 开源

A standalone, personality-driven multi-agent workspace application written in C, & C++