Custom agents

AI-powered developer onboarding platform using natural language to deploy applications via GitOps. Golden path workflows with ArgoCD and OpenRouter integration.

Validation and permission system for Claude Code

MCP server empowering AI assistants with real-world capabilities: Gmail, Calendar, Tasks, Git integration, and note management. Bridges AI assistants to external services through standardized protocol with secure authentication.

A simple task management system for managing AI dev in Cursor

Universal Agent Protocol (UAP) - Making AI agents work together seamlessly. The standard way for agents to find, talk to, and coordinate with each other in multi agent systems (MAS).

A self-hosted job alert bot for jobs that are actually remote (not just US-remote)

Framework for RAG over Excalidraw canvas data

Maps Claude Computer Use to Playwright

Agentic Workflow & Patterns implemented using Spring AI

Ask questions about your business data in plain English, Get automatic SQL queries and visualizations, Receive AI-powered insights and recommendations, No SQL knowledge required

Containerized A2A-native agents with simple setup

Local-first LLM wiki for research workflows with Obsidian, a dashboard, and a macOS menubar runtime.

EduAI is a modern, AI-powered learning platform that provides personalized education experiences through interactive courses, assessments, and gamification features. Our platform combines cutting-edge technology with proven educational methodologies to create an engaging and effective learning environment.

A powerful, multi-modal Telegram bot leveraging cutting-edge AI technologies including Gemini, DeepSeek, OpenRouter, and 50+ AI models for comprehensive conversational assistance, media processing, and collaborative features with MCP (Model Context Protocol) integration.

Apache Flink MCP Server is a Model Context Protocol (MCP) implementation that empowers AI assistants and large language models to interact directly with Apache Flink clusters through natural language. It enables intelligent monitoring, management, and analysis of real-time streaming applications—making stream processing more intuitive, accessible.

A plugin for Obsidian that replaces embed syntax with actual content for easier context sharing with AI language models.

:sunglasses: Simple ChatBot, which replies to anything you ask ! Now with voice recgnition ! Say "Hey" to wake the bot ! :D

Food recommendation chatbot with LLM fine tuning. 2023 graduation project from Pusan Nat'l Univ.

Very simple example of Seq2Seq model

Have a story to share? Feeling depressed? Want to give up? Feeling suicidal? HearMeNow is here to hear you out.

A chat-bot powered by Amazon Lex and built on top of Serverless Architecture

JanSevak is a AI powered HealthCare Management System. The system allows users to register as patients, book appointments, and predict diseases based on symptoms. Doctors can view and manage appointments. Additionally, the system provides information on various health-related topics through blog posts.

Intentional is an open-source framework to build reliable LLM chatbots that actually talk and behave as you expect.

For facebook comment and messenger fan page.

Chatbot Designed to Help Tenants Facing Eviction and Other Landlord-Tenant Law Issues

Rasa Chatbot using Django backend and Sockets for communication

TGPT - Lightweight GPT Telegram Bot built in Go

Some unofficial extensions to Kernel Memory to do some advanced RAG

WMB-100K — The first 100,000-turn benchmark for AI memory systems

Knowtate is a sophisticated platform designed to elevate your academic research experience. Seamlessly blend reading, note-taking with markdown, and knowledge management into one intuitive interface, allowing you to effortlessly track your insights and ideas as you delve into scholarly literature.

js client for R2R: production-ready RAG engine with a sh*t ton of features.

Retrieval-Augmented Generation (RAG) toolkit for Laravel: async docs, chat, outlines, multi-provider.

Perform intelligent research over document collections using hybrid search and LLMs.

In-memory vector database with pluggable indexing algorithms, metadata filtering, and a FastAPI-based REST API.

Official implementation of "RAViG-Bench: A Benchmark for Retrieval-Augmented Visually-rich Generation with Multi-modal Automated Evaluation"

RAG-Mathstar 智数星

本项目主要是2025届浙江大学软件学院夏令营（AI营）的考核项目

This project is an end-to-end Retrieval-Augmented Generation (RAG) system designed to ingest, parse, embed, and semantically search scientific papers from arXiv.

RagCheck is a proactive corpus quality assessment tool that analyses RAG application document collections before deployment, identifying content gaps and providing specific recommendations to improve query performance. The platform transforms reactive corpus fixes into proactive quality assurance, helping organisations achieve as high as 85% score.

技术周刊，每周一发布。前沿技术、社区资讯，一网打尽。

Exploring the use case of LLMs in healthcare, in particular assisting in document retrieval and summarization.

🚀 this project aims to develop an app using an existing open-source LLM with data collected for domain-specific Jenkins knowledge that can be fine-tuned locally and set up with a proper UI for the user to interact with.

This is an LLM agent for college students to study courses by themselves. Upload your textbook and enjoy the learning experience now!

Optimize Subtitles for RAG Ingestion

🔒 100% Private RAG Stack with EmbeddingGemma, SQLite-vec & Ollama - Zero Cost, Offline Capable

AI Search Engine in 70 lines

PDF AI Assistant Powered By Genimi

Convert any image into a Region Adjacency Graph (RAG)

This project is an automated research and summarization tool that allows users to conduct research on a specific question and summarize the information found and present it as a blog post.

Open-Source Java AI Assistant

An AI-powered search engine to interact with documentation using RAG and local LLMs. Privately deployable with vector search and a modern frontend.

SpeakingAI is a demo of privately deployable 'GPT-4o like AI + RAG', a fully functional web AI server with audio query/answer in streaming, using LLM and RAG for backend knowledge.

A CLI tool written in Go to chat with your pdf data

Web application for benchmarking and comparing LLM behaviour, energy and emissions on cloud and bare metal under different inference configs, middleware scaffolds and post-training implementations

An interactive Streamlit dashboard for visualizing TSLA OHLCV data with TradingView Lightweight Charts, enriched with trade markers, support/resistance bands, and an AI chatbot powered by Gemini.

For unmanned missions into GPT returning structured data

Open-source AI coding team with multi-expert orchestration

🦀 The first autonomous hackathon agent stop assisting and start competing (🏆 Hackathon Champion Project).

Compare agents pairwise via multi‑round evaluations for SE tasks.

Multi-agent swing trading system — automated screening, research, and execution with backtesting and live trading

Business-ready AI agent desktop app. Easy to install, free to run. Built with Electron and Lima VM.

Your Desktop, From Anywhere. AI-powered remote desktop control from your phone.

🛡️ Orchestrate Claude Code sessions via API. Create, brief, monitor, refine, ship. The bridge between your orchestrator and your coding agent.

Open-source AI desktop assistant — run local or remote LLMs with privacy-first design and zero setup required.

AI Agent plugin for Autoresearch with AI (Claude, OpenClaw, etc) to improve anything!

A comprehensive Model Context Protocol (MCP) server providing real-time YouTube Data API access for AI assistants. Features 14 functions including intelligent content evaluation with technology freshness scoring for knowledge base curation.

🤖 Your Agents' personal email 📧

An AI decision assistant that helps you think, decide, and act — powered by Spice.

Fast & less costly AI decision making and intelligent processing of multi-modal data.

This is an official repository for "Exploring Multi-Modal Data with Tool-Augmented LLM Agents for Precise Causal Discovery".

Local RAG system with a built-in governance agent that filters sensitive or restricted information with separated agent logging systems to keep privacy and security

Multi-agent orchestration for building production apps with Claude Code. 15 agents, 12-phase pipeline, from requirements to deployed.

Give your AI agents a chief of staff.

Autonomous Software Engineering Agents — self-healing, self-diagnosing development team powered by Claude Code and A2A protocol

Open source Golang LLM Proxy, Agent SDK with Restate & Temporal support for durable agent loop

Build an AI personal assistant using a multi-agent architecture to manage email, calendar, research, and travel planning. It integrates real APIs and runs via web, Telegram, and voice interfaces, powered by n8n workflow automation.

Open-source AI agent security framework. Score, harden, and govern your AI agents. Built on DoD/DISA zero-trust principles.

A fully autonomous asset manager on Abstract. Returns may vary.

A Git intelligence MCP server built with Node.js and TypeScript that analyzes local Git repositories to surface insights like hotspots, churn, temporal coupling, knowledge maps, and risk scoring. Designed for AI agents, it exposes repository analytics tools through the Model Context Protocol (MCP) while keeping all data local and read-only.

Model Context Protocol based AI Agent that runs a browser from Claude desktop

Maven is a cutting-edge web application that leverages the power of AI to revolutionize electronic categorized product research and data-driven decision-making.

Local-first AI agent mesh in Rust. Hard budget enforcement, adaptive model routing, and end-to-end OpenTDF encryption. Built for individuals and small teams.

将 Google Gemini 网页进化成本地 IDE 的浏览器插件

Morning Deck is an open-source, self-hostable AI-powered news intelligence platform.

Deterministic context database for AI agents. Same query → same context, every time.

Elixer AI is a RAG-enabled LLM platform for secure, 100% accurate biomarker-based medical report analysis. It supports blood, urine, stool, sperm, and pap tests, with future-ready vision-LMM integration for imaging, plus EHR, hospital, and appointment support—built on React, Node, MongoDB, AWS, and Gemini AI.

[ICML 2024] Official repository of ICML 2024 - RoboMP2: A Robotic Multimodal Perception-Planning Framework with Multimodal Large Language Models

Simple Golang RAG Server

This application allows users to upload PDF files, process them, and ask questions about the content using a locally hosted language model. The system uses Retrieval-Augmented Generation (RAG) to provide accurate answers based on the uploaded PDFs.

EverMemOS memory backend plugin for OpenClaw — long-term memory, retrieval, and progressive profile building.

RAG Hallucination Detecting By LRP.

Financial Literacy Gamification is a Minecraft-themed web app offering expert sessions, blogs, stock analysis games, and multi-player parties. It features a rewards system, real-time dashboard, and a chatbot for document support. Users engage in interactive learning, quizzes, and battles to boost financial skills.

Offline local-first personal knowledge base with document upload, vector search, and Ollama-powered RAG chat.

A tool for converting HTML and RST docs into Markdown, and loading them into PostgreSQL.

CellphoneS Chatbot là trợ lý AI giúp khách hàng tra cứu thông tin sản phẩm, chính sách và dịch vụ của CellphoneS bằng tiếng Việt, kết hợp công nghệ RAG và giao diện web hiện đại.

Vidhi.ai is an intelligent legal assistant and navigator built to make legal knowledge and government processes accessible for everyone in Nepal with well-cited answers grounded in authentic Nepali laws and acts.

This repository explores the integration of Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) for reasoning and question answering in the domain of Unmanned Aerial Vehicles (UAVs).

Personal GitHub profile showcasing expertise in AI/ML engineering, generative AI, data science, and scalable production-ready solutions.

Swift Agent Package

🤖 An AI-native CLI Tool and MCP server for .NET memory dump investigations. Leverage LLMs (Claude/Gemini) to analyze heaps, threads, and exceptions using natural language. Built with ClrMD, token-efficient paging, and Docker support for cross-architecture (.NET/AMD64/ARM64) post-mortem analysis.