Custom agents

A Model Context Protocol (MCP) server that provides agentic search capabilities with support for vector search using Qdrant, full-text search using TiDB, or both combined.

Ultrarunning training companion agent powered by Intervals.icu.

Build a full‑stack helpdesk system with autonomous multi‑agent AI for ticket resolution and escalation.

🚀 End-to-End Industry-Ready Projects

Vibe Innovation und Vibe Coding Workshop mit GitHub Codespaces

The Self-Learning AI Framework is an autonomous system that analyzes, modifies, and optimizes its own code. It supports natural language interaction, framework creation, code suggestions, PDF-based learning, and package management. Ideal for automating code reviews, agent creation, and AI-driven development.

An MCP server that empowers AI assistants (Cursor, Claude, Cherry Studio) to search, read, and summarize arXiv papers directly.

AI Workspace Assistant for company

🌀 The world's first emotionally intelligent CLI that thinks, creates, and empathizes with developers. Autonomous AI with Vision, Dream Engine, and Emotional Intelligence.

A chat bot to summarize, fetch and give the pre requisites for a research paper

Backend for the social media bot

AI-Butler is an innovative project that uses artificial intelligence to act as a virtual assistant. From taking simple notes to providing intelligent insights based on their context.

Negochat Corpus - a dialogue corpus in the negotiation domain

An Omegle Chatbot for promotion of Social media content or use it to increase views on YouTube. With the help of Chatterbot AI, this chatbot can be customized with new QnAs and will deal in a humanly way.

Chat bot for TruckersMP that provides server stats, player count, events, and AI chat powered by GPT

Implementation of "Distilling Knowledge for Fast Retrieval-based Chat-bots" (SIGIR 2020) using deep matching transformer networks and knowledge distillation for response retrieval in information-seeking conversational systems.

AI voice-activated girlfriend assistant with wake word detection, speech recognition, and animated GIF overlay. Powered by Liebea Model, Whisper.cpp, and Edge-TTS.

Links the Discord chat and the Twitch chat together.

Enterprise WeChat (WeCom) channel plugin for OpenClaw

适配OneBot, C++开发的聊天机器人

End-to-end QLoRA-based fine-tuning of Llama-2 for a medical-diagnosis/doctor chat-bot on AWS

NEW VERSION AVAILABLE : Basic Chat-Bot Design developed in 8 stages... From here you can design and build your own chat-bot, connect to external API etc...Archived lessons -UPDATED TUTORIAL HERE >>>>>>>>>>>>>>https://github.com/spydaz/Chatbot_2020_Tutorial

KECRA (Knowledge-Enhanced Cobot Reasoning Assistant ) is a framework for language-based control of collaborative robots (cobots) in dynamic construction environments. It combines Large Language Models (LLMs) with Visual Foundation Models (VFMs) to allow human operators to guide robotic assistance through natural language dialogues.

NoLlama is a lightweight terminal-based interface for interacting with Large Language Models (LLMs) from major providers or from your local ollama instance.

AI Chatbot & Ticket Answering System for Web Hosting

Fluid dialogue manager plugin for Godot 4.x built on RiveScript

Don't wait any longer! Free ChatGPT now in your WhatsApp chat. Bing Bot https://github.com/andresayac/bot-wa-bing-ai

Classical music exploration chatbot built using Embabel and Neo4j

Highly Advanced and Best Telegram Group Modular Bot inspired from @MissRose_Bot and Yone Bot

Chatbot for Astro Sites

Build your own generative UI chatbot using the Vercel AI SDK and Google Gemini - TanStack Start

An example of how to make a chatbot in discord.py using dialogflow/api.ai. Currently using older versions of dialogflow (v1)

Matrix Sticker Import Bot is an open-source tool that enables users to seamlessly import Telegram stickers into their Stickerpicker instance using a Matrix bot. The project includes a Docker container that integrates Stickerpicker and MStickerEditor, providing each user with their own customizable sticker packs.

Claude Code in Feishu. WebSocket streaming, all message types, doc auto-fetch, zero-cost.同类型也有 cc-connect，但cc-connect 为了兼容 9 个平台 6 种 Agent，架构上必须做抽象层，消息要在平台适配器和 Agent适配器之间来回转，链路长了自然慢。feishu-bridge 只做飞书到 Claude Code这一条直线，没有中间层，消息直接透传。多平台是 cc-connect 的优势，但如果你只用飞书，那些适配代码就是纯开销，既拖速度又加故障点。

GenAI with Google Gemini: 5 transport approaches REST → Streaming → SSE → WebSockets → gRPC

🗣️ A free, open-source tool that enables you to create custom chatbots from simple Markdown files

Build a WhatsApp chatbot using this demo tutorial powered by Node.js and Wassenger API 🤖 🤖

Gradio-based web UI for medical image interpretation using Google's MedGemma vision-language model.

A chat bot that notifies you about new paragliding cross-country flights.

CharacterAI telegram chatbot. Made using Aiogram 3.

Blenderbot

nanograd🧠 ML/DL and neural net ecosystem, run models like GPT, llama, stable diffusion, vision transformer, reinforcement learning, autotrainer, your Unreal Engine, but for AI, essentially making it an AI engine or an AI Ecosystem

A lightweight observability platform for LLM applications. Track costs, latency, and quality across your AI systems with minimal overhead.

Intelligent text chunking for RAG (Retrieval-Augmented Generation) and LLM applications in Crystal.

Graph RAG visualization platform with interactive knowledge graphs and real-time parameter tuning for local LLMs

This project implements a Retrieval-Augmented Generation (RAG) system using GraphRAG for the novel "86 - Eighty Six"

All Materials from my workshops

Local-first tool for analyzing GitHub issues and generating triage recommendations using AI.

LLM Engineer's Handbook by Paul Iusztin and Maxime Labonne with pixi.

The trusted state layer for persistent AI agents. Structured cognition, audit-grade observability, MCP-native. Self-hostable. ELv2.

Rearview: Review your broswer knowledge with AI-Powered search.

Three-layer memory architecture for long-term AI learning with Claude

OpenViking knowledge base integration for nanobot — RAG augmentation, semantic search, vector embeddings, document indexing. Free models on SiliconFlow.

Local, privacy-preserving semantic document search engine with citation verification

Local AI server with persistent memory, RAG, and multi-backend inference (MLX / llama.cpp / Ollama). Runs entirely on your machine — zero data sent to external services.

Experience a fully local, Spring AI-powered CLI chatbot using RAG, supporting various document types for domain-specific Q&A—all running entirely on your machine with no external services required.

A Tomb Raider Custom Level management application

A Module for Large Language Models that seek to integrate a vector-based memory system into the inference process, leveraging embeddings to capture deeper semantic meaning.

Implementation of autonomous AI agent(s) in JS using Webworkers

An AI-native, lightweight web kanban board for tmux sessions and terminal agents.

MCP server for Bloomfilter, a domain registration service for AI Agents.

OpenClaw-oriented workspace template for AI-agent continuity: file-based memory, self-identity docs, and operating conventions.

Run.dev is an AI-native local development environment built in Rust. It manages all your services from one TUI dashboard — automatic .local domains with HTTPS, SNI-based reverse proxy, live CPU/memory stats, and Claude Code integration for crash diagnosis and live debugging. One binary. Zero config files.

Steuermann is designed as a domain-agnostic, on-premise AI runtime. It can be extended with profiles to adapt to specific use cases.

Active development continues at ScopeBlind/scopeblind-gateway. - Security gateway for MCP servers. Cedar policy engine, Ed25519-signed receipts, per-tool enforcement. IETF Internet-Draft. 4 patents pending. npx protect-mcp

Proactive personal AI agent with scheduled nudges, smart suggestions, and context-aware assistance

AiTaxs 综合财税 AI 助手skill

Java integration for Claude Code CLI. Features Virtual Thread execution, Spring Boot auto-configuration, Kafka request-reply adapters, and REST/SSE streaming endpoints.

无需ROOT，无需ADB，让AI控制你的安卓手机

No longer maintained.

Flowrabbit® Studio is an open-source, low-code platform for UI/user-centric GenAI workflows. It is best used for human-in-the-loop use cases.

The community version of the Web Speed mapping tool

This repository is continuously updated with new architectures and improvements to stay at the forefront of AI agent design.

Why We Built One of the First Open-Source Voice AI Orchestrators in Go. Lokutor.

Installable Codex skill for long-running autonomous coding refinement loops with validation and resumable state

Multi-source cross-validated memory MCP server for AI agents (Rust, jieba CJK, local-first, AGPL)

Nix flake framework for distributing, propagating, and sharing agent skills

Outcome-focused parallel agent desktop application that replaces chat-driven AI workflows with a goal-first model.

📞 Локальный AI-секретарь, тех. поддержка и менеджер по продажам с клонированием голоса XTTS v2, real-time распознаванием речи (Vosk/Whisper) и offline LLM (vLLM + Qwen/Llama и тп). Полноценная админ-панель (Vue 3), Telegram-бот, виджет для сайта, fine-tuning pipeline. Self-hosted, приватность данных, СМС и телефонные звонки .

AI Skill 安全扫描：安装前查危险命令、提示注入与密钥泄露，可作 GitHub Action｜Security scanner for AI agent skills

AI-native agent framework for Go.

LLM-powered game agents for chess, Go, poker, social deduction, and 20+ other games

Agent-native financial research in your terminal. Like Bloomberg but without the subscription.

AI-powered job application automation with GPT-4o, LinkedIn auto-connect, resume optimization, and cold email campaigns. Features AI agents for contact ranking, scam detection, and memory layer for learning from successful outreach.

A 7-agent pre-release audit pipeline for software products. Generic, reusable, AI-native. Inspired by Garry Tan's gstack.

Python SDK for the Carbonyl terminal browser. Persistent named sessions, daemon mode, realistic browser fingerprinting, screen-text inspection, and host-browser cookie import. Lightweight Selenium/Playwright alternative purpose-built for LLM agents and scraping that needs a real browser but not a real display.

Agent-interpretable data-science tools, evolved via autoresearch.

Agentic Environment Optimization for Autonomous AI Agents

OpenClaw Execution Firewall - Seccomp-locked AI agent sandbox with policy-enforced command governance, WhatsApp/Telegram integration, and Python isolation. Deploy on Oracle Cloud Free Tier.

Your local long-term memory for AI agent interactions. Parse, classify, search, and visualize every interaction with Claude Code, Codex CLI, Claude Desktop, and ChatGPT.

Turn MetaTrader 5 into a REST API server for algorithmic trading - supports historical candles, account data, and trade execution via HTTP.

PhantomEar is a privacy-first, local-only AI meeting assistant that runs invisibly on your machine. No bots, No cloud recording, No admin permissions.

Decentralized communication infrastructure for AI Agents — DID identity, federated discovery, E2E encryption, session management, and MCP-native integration.

EdgeTales - A Narrative Solo RPG Engine

For OpenClaw, Hermes and more. Find free and low-cost inference (LLM models). Use them directly. Provides both a CLI and MCP server that knows which free-tier LLM APIs exist, which ones you have keys for, and which one fits your task. Returns endpoints so can you call models directly. No proxy, no middleware, no latency tax.

Deterministic, scriptable CLI and live TUI for Planka kanban — built for shell scripts, CI/CD, and AI agents.

Lightning-fast RAG for AI agents. ONNX-powered, 4-layer fusion, MCP server. No PyTorch.

Autonomous AI agent loop that keeps working through your project while you keep planning what comes next.