C++ agents

Robotics demos: ROS, SLAM, robust control, mobile robotics.

Modern, header-only C++ library for Retrieval-Augmented Generation (RAG) with Ollama-hpp.

A cross-language, cross-platform framework that gives all AI Agents the ability to "Jiezhu" (接住/Catch) — to catch you steadily, emotionally, unconditionally.

The game engine for agents.

Natural language to ROS2 actions — a structured LLM grounding engine for any robot.

A GUI application for creating task assignment formations of NAO humanoid robots in SPL.

A chatbot in C++ implementing AIML.

A smart home automation system that brings the power of a virtual assistant to your IoT devices. Inspired by the famous AI assistant "JARVIS" from the Iron Man series, this project combines cutting-edge embedded technology with natural language processing to create a seamless and intuitive IoT control experience.

The Universal LLM Gateway - Integrate ANY AI Model with One Consistent API

The first fully MCP 2025-11-25 compliant C++ SDK - Build production-ready MCP servers and clients with complete protocol support including Streamable HTTP transport and OAuth-based authorization.

Little gguf - a tiny, embeddable, fully functional direct quantized inference engine for llama/qwen models in standard gguf format; no dependencies

Texas Hold'em AI System | Poker AI Bot | Poker Simulation | Game Theory AI | 德州AI源码，德州源码，德州扑克人工智能AI，1对多的德州AI，可以战胜人类职业牌手，全套AI源代码和AI训练模型，德州AI源碼，德州AI輔助軟體，德州撲克人工智慧AI，1對多的德州AI，可以戰勝人類職業牌手，

deep (Dynamic Epistemic logic-basEd Planner) is a multi-agent epistemic planner that operates over the full scope of mA*, leveraging optimized search algorithms and heuristics.

Independent Cardputer adaptation of Anthropic's claude-desktop-buddy for M5Stack Cardputer QWERTY and BLE

Enable autonomous creation and management of Unreal Engine game projects using AI-driven editing of Blueprints, code, and assets within the editor.

Provide AI-driven penetration testing with portable hardware tools tailored for cybersecurity research and real-world testing scenarios.

Single-process database for AI apps: vector, graph, lexical, and hybrid search with durable jobs in one binary.

A self-improving intent engine for autonomous work.

Sensor-level micro AI Agent in C/Rust 鈥?<1MB RAM, runs on $2-5 MCU hardware like ESP32. The smallest member of the Claw family.

A bridge for AI to interact with UE5

An Android AI Agent (toy project) combining a native C++ daemon with AI capabilities.

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

A chat bot using various LLM models. It runs locally using your own GPU and/or CPU.

A Twitch chatbot written in C++/SFML with IRC interface

A chat bot powered by chat GPT.

ilotterytea's twitch bot.

A C++ OpenAI CLI interface! I use this as my day-to-day toolkit for working with OpenAI products.

Tabular Q learning to demonstrate sample OpenAI taxi V2 implementation in C++

Root Cause Analysis of Task Plans implemented using BehaviorTrees using ChatGPT

AI for Anti-Malware Research

Turn any desktop app into an agent-ready API.

A cutting-edge, real-time security monitoring system, designed to revolutionize your network's defense

Native C++17 AI agent runtime — local-first, embeddable, MCP-native. Tool-calling, memory, and an async agent loop that runs where Python can't: ROS2, game threads, drones, HFT.

The agent-native video editor for music & shortform: voice conversion, lyric & karaoke videos, auto-subtitles, and a full FX stack. AI drives the real timeline over MCP. Linux-native C++/ImGui, zero dependencies.

A (nearly) fully featured and up-to-date c++ clone of the openai-node library.

Run powerful AI models entirely on your Android device. 100% offline, private, no API keys. Built with Kotlin, Jetpack Compose, Material 3, and llama.cpp. Download GGUF models from Hugging Face. On-device LLM inference for Android.

C++ AI Agent like langgraph. 支持嵌入普通 app 中辅助实现ai功能

德州源碼 | 德州撲克源碼|团队多年研发的德州扑克AI，支持1对多，包括1对9，对于gg，wpk，hhpoker，AApoke等平台的玩家都有很大帮助的，提升玩家的德州水平；TG：@xuzongbin001；

An Agent Skill + UE5 C++ plugin that gives AI agents full control over the Unreal Engine 5 editor.

IEE is a native C++ system runtime that converts live OS/application state into a deterministic, queryable, and executable intent layer. It is built as an execution substrate and control plane, not a UI product.

Edit text anywhere with AI! ✨

Leo is a 3D interactive AI assistant built with React Three Fiber, ElevenLabs, and Blender models. It features real-time voice interaction, lip-sync using Rhubarb, and a sleek, lifelike avatar for immersive communication.

A cross-platform chatbot app using OpenAI API, built with Flutter. This project enables users to create and customize a chatbot application for Android, iOS, and the Web. Perfect for task automation, personal assistants, or experimental AI integration.

OLAMI API Quickstart C++ Samples

C++ header-only implementation of VaneDB — embeddable vector database for edge AI. See vanedb/vanedb for the Rust crate (PyPI, npm, WASM).

C++20 framework for LLM application and AI agent orchestration: typed components, Chain/Graph workflows, streaming, callbacks, and unified execution.

Native agent-graph runtime written in C++20

Stream responses from OpenAI and Anthropic models with lightweight C++ tools for efficient large language model integration.

Fogot - A custom Godot engine fork with AI-powered editor

Independent LangGraph C++ runtime for stateful AI agents and recoverable graph workflows: checkpointing, streaming, interrupts, tool calling, edge/local LLM apps. C++23 developer preview; not official LangGraph/LangChain.

An spoken English chatbot runs in realtime and offline based on LLM.

AI Camera is a smart image recognition system built using an ESP32-CAM, I2C LCD, and a button trigger. On pressing the button, it captures an image, sends it to OpenAI’s Vision API through an n8n workflow, and displays the identified object(s) on the LCD screen and Serial Monitor. It’s a compact and low-cost AI-powered vision device.

Composable Agent Infrastructure — HTTP/WebSocket Gateway, Persona Runtime, Semantic Memory, Real-time Vision, and BERT/VLM Inference in C++20

Qt AI Chatbot for which supports MCP tool calls and RAG, written in C++ with Qt. Uses Ollama for the backend.

🤖 小智开源音乐固件 | ESP32 AI聊天机器人，支持智能音乐播放和微信留言推送 | Xiaozhi AI Music Robot with WeChat Message Push

Manage Notion from the terminal — faster than MCP. 19 commands, C++23, pre-built binaries.

Offline speech-to-text & speaker diarization for AI agents — Whisper ASR + MCP server + CLI + Python bindings, fully on-device, no cloud | 离线语音识别与说话人分离,Agent 开箱即用

Este proyecto utiliza un ESP32 para monitorear las condiciones de una planta (humedad y temperatura) y transmite los datos a través de WiFi. Los datos se procesan y se utilizan para generar respuestas sarcásticas personificando la planta al combinar la electrónica y la API de OpenAI.

A bridge between Fllama (llama.cpp for Flutter) and Langchain for Dart.

A headless terminal emulator built for native Windows OS, that keeps `isatty()` returning `true` for spawned processes while staying either completely invisible or hiding in system tray. Run any TTY enabled app such as Claude Code CLI, Gemini, Codex, or any TUI app without a console.

Provide an AI desktop assistant that supports OpenAI APIs, offers interactive workflow help, and runs on macOS 13+ and Linux (Wayland).

This python powered AI based RAG Scraper allows you to ask question based on PDF/URL provided to the software using local Ollama powered LLMs

A portable, offline-first CLI AI assistant built with C++ and llama.cpp. Features dynamic file context awareness, memory management, and runs entirely from a USB drive without dependencies.

⚡ High-performance AI coding agent for the terminal, built in modern C++23. Multi-provider LLM support (Anthropic, OpenAI, Ollama), 9 built-in tools, interactive REPL, and session persistence.

Zero-dependency single-header C++ library for streaming OpenAI & Anthropic LLM responses. Drop in llm_stream.hpp and go.

ESP32-S3 personal productivity assistant with Groq AI, Telegram bot, real-time Web-UI, habit tracking and Pomodoro timer. Built with FreeRTOS, Arduino C++ and 3368 lines of code. 96.4% software uptime.

Fast, lightweight, cross-platform IDE built with C++17 and Qt 6. AI assistant, LSP intelligence, integrated terminal, Git — native performance, no Electron.

C++ inference runtime for llama.cpp that shares a single document KV-cache prefill across multiple analytical branches via snapshot fan-out. Eliminates redundant GPU compute and dramatically reduces TTFT in DAG-based multi-agent pipelines.

Headless CLI for Kdenlive — manipulate .kdenlive project files from the terminal by calling Kdenlive's own internal APIs directly.

Token-efficient context engine for AI coding agents. v2.21.0: brain+token trio — session-aware recall delta, contradiction sentinel, adaptive recall depth. 2416 tests, 42 MCP tools, Elastic-2.0.

Manage multi-turn conversations efficiently with a lightweight C++ library from the llm-cpp toolkit for LLM infrastructure.

Lightweight AI assistant plugin for Notepad++ with visible prompts and single-turn behavior

The thread through any AI labyrinth. C++ LLM workflow orchestration.

Stop AI agents before they do damage — behavioral sequence detection blocks credential exfiltration, config harvesting, and secret leakage before the network call fires

AI-Powered n8n Automation Suite - Transform your business operations with cutting-edge AI automation workflows built on n8n. From smart email responses to custom chatbots, automated content publishing, and intelligent complaint management, these are enterprise-grade automation powered by LLM Models.

Multi agent path planning

HierLearning is a C++11 implementation of a multi-agent, hierarchical reinforcement learning system for sequential decision problems.

Hold a key, speak, get context-aware AI-polished text typed at your cursor. Windows native, BYO Azure/OpenAI keys, MIT.

AI-Waifu is an IoT voice assistant developed for the ECL-108 IoT Workshop. It uses two ESP32 DevKit boards communicating via UART to capture voice input with an INMP441 MEMS microphone and produce speech output through a MAX98357A I2S amplifier. The Google TTS API generates responses in a Japanese female voice.

Nikola — autonomous AI system based on ATPM consciousness architecture. Nitpick is its primary language substrate.

MCP server plugin for Unreal Engine 5 — control the live editor with AI clients (Claude, Cursor) via 43 tools. Spawn actors, edit Blueprints, manage assets & run scripts directly from your AI assistant.editor-plugin

C++23 framework for building LLM-powered agents with tool use, structured output, multi-provider