Custom agents

MIDAS is an open platform for governing execution authority at decision surfaces across agents, AI systems, and enterprise workflows.

基于 Yui 的机器人框架. 无electron依赖

Bot moderator for your telegram chat

A self-hosted AI toolkit running locally via Docker Compose, bundling an LLM gateway, workflow automation, and a chat UI — all backed by a shared PostgreSQL database.

No more guessing. No more panic after a bad patch. No encoding surprises. A protocol for safer, smarter updates — the bigger your codebase, the more it pays off.

Coordinate AI agents in a workflow

Microsoft Agent Framework 워크샵 자료입니다

LimeBot Open Source a self-hosted, agentic AI assistant with multi-channel support, persistent memory, and a real-time web dashboard.

🤖 A lightweight chatbot that knows nothing and has to learn from scratch. Using sqlite and python. Also comes with a Discord intergration 🗣

This project lets you create a chatbot of your own which would respond to text messages just like you would have. All you need to do is supply your WhatsApp chat backups (details in the README file) for training the model. No data is collected or shared with anybody. Note: This bot is not integrated with WhatsApp in any way and hence would not reply to your incoming texts automatically.

A Minecraft anarchy server chatbot

Langflow chat proxy and frontend using FastAPI and HTMX

This is a chat bot web app created with an open source AI Large Language Model Called BLOOM

An advanced AI-powered conversational agent leveraging the Llama 3.2 model and Phidata framework. Features include reasoning, natural language interaction, and tool integration for web searches and calculations. Designed for interactivity with enhanced logging, support for custom tools, and structured outputs.

A sophisticated trading system leveraging local LLM deployment through Ollama, distributed computing with Apache Spark, and vector-based episodic memory using ChromaDB to make intelligent trading decisions.

This repository introduces a Gemini CLI extension that integrates File Search feature. This tool provides a fully managed Retrieval-Augmented Generation (RAG) system directly in your command line, enabling content generation grounded in your private documents and data.

🧑‍⚕️ Ai智能医生聊天助手-这是一个前端基于Vue3、TS、后端基于Nest.js、MongoDB、Redis、Milvus并结合大模型、RAG等技术实现的医疗库智能问答系统，能结合大模型的生成能力和上传的专业医疗领域知识库针对提问给出专业回答。同时具备工具调用能力，可使用MCP集成网页爬取能力让大模型根据网址对应的医疗领域文章进行分析和输出。

AI-powered tool to run old Windows games on macOS via Wine — automatic configuration, no manual setup. Supports Apple Silicon and Intel.

Give AI agents eyes and hands inside your live React app — no browser extension required

Local-first desktop workspace for creating, versioning, comparing, and shipping AI Agent Skill assets.

OKR lifecycle management skill for AI agents. Create, track, and report on Objectives and Key Results.

TaxEase.AI is a user-friendly AI assistant designed to demystify and simplify US tax filing, a system that has become needlessly convoluted and stressful for millions of Americans.

Agentic IQ - $AGENT

Pure CLI + HTTP messaging gateway for routing channel messages to external agents.

AI code review MCP server with Zero-Trust approach. Multi-model support, caching, multilingual. Works with Windsurf & Claude Desktop

personal-cfo , Reference implementation — 展示非專業投資人如何用確定性運算做退休軌道監控。銀行帳單進，財務報表出，資料留在本地。Fork 後依照你的情況改 config.yaml 就能用。

A Baseline for an Omnipotent AI Data Catalog

Minimal tmux popup radar for Codex, Amp, Claude Code, OpenCode, Pi, Gemini and Auggie.

Connect agents to agents. MCP server for querying any LLM through your existing subscriptions: compare, vote, and synthesize across GPT, Gemini, Claude, and local models from one terminal.

OneSDK: A unified AI access SDK for edge devices, providing LLM capabilities (text/voice chat, image generation) and IoT device management with MQTT support, compatible with ESP32, Linux, macOS, and Windows platforms.

A fully client-side chat application with AI capabilities running entirely in your browser. No servers, complete privacy, and persistent storage.

Generate reliable data visualizations from LLM output using validated specs.

Autonomous AI Agent built on tinyloom

CLI Ralph Loops with Good UX

Principal Agent Protocol — a principal-first, zero-trust agent negotiation protocol for the open web

Execution-control runtime for AI agents: budgets, cancellation, circuit breakers, and observability—delegating heavy work to external worker CLIs.

Deploy parallel AI agent swarms for planning, implementation, and code review — a Claude Code plugin.

Reduce your OpenClaw agent costs. Free real-time LLM cost tracking + dashboard. Installs in 60 seconds.

Lightweight TUI dashboard for Claude Code token usage, agent sessions, and system resources. Go.

Virtual MasterCards for AI agents - pay with USDC via x402 on Stellar

AI Swarm Agent Launcher - A powerful CLI tool for launching and coordinating AI agents with specialized personas using git worktrees

claude-devkit - an agentic coding framework

Analysis that sees what you don't. 7 cognitive lenses + solution engineering for Claude Code.

Battle-tested skills for AI agents that do real work

Self hosted secure gateway for AI agents. One token. Full control. Complete audit trail.

基于 Expo + React Native 构建的现代化、纯净、无广告的跨平台传统文化工具。应用致力于将传统国学与现代化的移动前端技术和人工智能分析系统相结合。

Maven Lightning Lesson on Product Thinking for Agentic Development - Specflow framework, patterns, and live tnyOffice demo

Generate AI context for your dev stack — works with Claude Code, Cursor, Windsurf, GitHub Copilot, Gemini CLI, or any LLM.

⚙️ Enable AI agents to conduct autonomous penetration testing on any Linux distribution with a persistent and robust Model Context Protocol server.

A curated list of awesome Pinecone resources, libraries, tools and applications

Real-time guardrail runtime for AI agents.

Declarative firewall for OpenClaw tool calls.

SANCTIS is a cognitive architecture that gives LLMs structured tools to organize their own reasoning, maintain long-horizon coherence, and reduce drift. It installs stable thinking patterns that emerge more powerfully the longer the model runs.

Architecture Deep Research: deep research for strategic system design decisions.

Launch, watch, and command your Cursor agents from one terminal

Mainnet-first Tempo MPP automation starter with workflow orchestration, spend caps, and provider safety controls.

AgentOrchestrator - Multi-agent development coordination platform. Transform AI assistants into sophisticated project planners that orchestrate teams of specialized agents for complex development workflows.

This is a fork from Ryan Carson's AI Dev Tasks repository, with some code cleanup and refactoring to enable support for PostgreSQL databases.

Save your tokens!

The high quality agentic ai Solana harness ✨ like openclaw 🦞 but specialized for Solana 👽 make trading bots, launch bots, build strategies, trade prediction markets and do research. Made with bun, solana/kit 6, Svelte, Helius, and more. Very gud tek 🤌🏼

Searchable Markdown KB built for AI workflows. Hybrid search, typed relations, wiki links, graph views. Token-efficient CLI for agents, static publishing for humans.

Validate your remarkable idea with Claude Skill. 用 AI Skill 验证你的好想法

end-to-end fullstack and real-time discord clone, all with servers, channels, video calls, audio calls, editing and deleting messages as well as member roles.

Community Regularization of Visually Grounded Dialog https://arxiv.org/abs/1808.04359

The kernel layer for production AI agents

Xaibo is a modular agent framework designed for building flexible AI systems with clean protocol-based interfaces.

Make Agent CLI is a powerful command-line tool designed to streamline the management and deployment of AI agents across multiple chains. This tool simplifies the process of making your AI agents discoverable and registering them as plugins.

MCP server that execute applescript giving you full control of your Mac

Branch-Thinking MCP Tool A TypeScript-powered MCP server for managing parallel branches of thought, semantic cross-references, and persistent tasks. Features dynamic scoring, AI-generated insights, batch operations, and visual graph navigation for advanced agentic workflows.

Safety proxy for your AI Agents

Using AI Agents for Audit SBOMs for OSS Compliance

Convert LinkedIn data exports to clean Markdown for LLM analysis & PDF resume generation. Zero-dependency Python CLI tool for AI career intelligence.

A telegram chat bot for : Getting lyrics, Getting nearby restaurants and their menu and random quotes.

The Developer Conference São Paulo 2018: Crie um chatbot para chamar de seu

Bot framework for Max messenger — router, middleware, context

Tiledesk Module for Conversational AI. Tiledesk is an open source conversational platform alternative to Intercom, Zendesk, Drift, Tawk.to and Tidio for Customer Service and Conversational Marketing.

Healint is a way to assist doctors and patients in disease diagnosis and their treatment. It has a doctor bot which interacts with patients and finally predict the disease. Other than this it also has location based hospital recommendation system. It also facilitates in knowing your BMI and getting a diet chart

Google Alexa like Laptop assistant written in Python which uses google's speech-to-text library to process voice input.

Intelligent AI Chatbot For Autism Spectrum Disorder.

Darvin is a Python-based voice-activated chatbot that interacts with users via microphone and speaker. It can perform web searches, play music, tell the time and date, fetch weather information, and provide Wikipedia summaries on command. Utilizing various libraries such as speech_recognition, pyttsx3, requests, pygame, and wikipediaapi.

This project is an online platform designed to provide comprehensive health services for cancer patients. The aim is to create a digital space where patients can easily access resources, support, and professional consultations to manage their health journey. Through this platform, patients and their families can find essential information.

🤖 :open_file_folder: Node.js Multi-page Bot Framework for Facebook Messenger

Chatbot-GPT, powered by OpenIM’s webhooks, seamlessly integrates with various messaging platforms. This tool enables private and group chats with bots, enhancing interactive communication. It delivers quick, automated responses, ideal for optimizing customer service and dynamic discussions, meeting diverse communication needs.

A chatbot for querying from Wikidata and Dbpedia

한국공학대학교 AI 챗봇 산돌이 배포용

React JSX factory implementation for Slack

WooCommerce MCP Server — WordPress community plugin implementing the Model Context Protocol (MCP) for WooCommerce. Supports STDIO and HTTP streamable transport, with optional JWT authentication. Based on Automattic’s official WordPress MCP. This plugin is not affiliated with Automattic.

Auto reply suggestions to chat messages/emails (like gmail and linkedin) built using rasa_nlu framework.

A Signal bot that replies to incoming messages with LaTeX PNGs

Minimalist Bash agent && copilot starterkit (OpenRouter)

This repository contains a customized version of N8N, an extendable tool for workflow automation. This customized version is focused on chatbots development, integrating nodes that allow to connect chatbot development platforms like Dialogflow.

ytLiveChatBot is a golang library for cli base applications that makes it easy to read and write live-chat on/from youtube live streams using youtube api.

Community-driven collection of open demos, tutorials, and deployment examples for building and running LLM-powered applications.

A Twitch bot to make your stream incredibly interactive

A frontend for large language models like 🐨 Koala or 🦙 Vicuna running on CPU with llama.cpp, using the API server library provided by llama-cpp-python. NOTE: I had to discontinue this project because its maintenance takes more time than I can and want to invest. Feel free to fork :)

A chatbot for Misskey with Markov chain

🤖 The Web App of the Curiosone bot.

Chatbot with personality using DialogGPT from huggingface (Rick bot).