GitHub agents

A Document-based QA Chatbot with LangChain, Chroma and NestJS

Stop writing Terraform by hand. A multi-agent framework that researches, generates, validates, and commits production-ready AWS infrastructure modules through conversation.

NeuralCache is a drop-in reranker for Retrieval-Augmented Generation (RAG) that learns which context the model actually uses.

Part of the LangChain.NET project. Has separate abstractions, does not contain dependencies on the main project and can be used independently

Multi-agent RAG system using AutoGen for document-focused tasks in medical education, leveraging LangChain, ChromaDB, and OpenAI embeddings.

This project has implemented the RAG function on Jetson and supports TXT and PDF document formats. It uses MLC for 4-bit quantization of the Llama2-7b model, utilizes ChromaDB as the vector database, and connects these features with Llama_Index. I hope you like this project.

a QA bot on contents of given docs 用所给文档进行问答的聊天机器人

Open AI APIs with Llama Index and Milvus Vector DB for Retrieval Augmented Generation (RAG) testing

Multi-agent Claude Code you can actually control. Spawn specialist teams in tmux, watch them work side-by-side, steer when needed. Built on native Claude Code agents. No black boxes.

[IROS'25] COCMT

Distributed AI Agent Framework

Made for a reading group at the Center for Safe AGI.

It shows an intelligent agent based on LangGraph for long form writing.

Hive is a Multi Agent Orchestrator modelled after Agile Teams

We use policy gradient to help agents learn optimal policies in a competitive multi-agent contextual bandit setting

Decentralized multi-agent collision avoidance

Mandali (मंडली) — Autonomous multi-agent adversarial collaborative system using GitHub Copilot SDK

The governed AI agent platform: semantic memory, intelligent model routing, an MCP server, and 67+ integrations.

multi-agent car parking using reinforcement learning

Deterministic agent runtime with explicit plans, typed tools, permissions, and replay. Implements Google DeepMind's Intelligent AI Delegation framework. Named after ELP's Karn Evil 9.

event-sourced adk for go

SmartAgentic is a project-centric, multi-agent memory OS for software engineering. It turns conversations and code decisions into an evolving knowledge graph so teams keep context across sessions, reduce contradictions, and ship.

The simplest way to deploy, manage, and scale AI agents in your Kubernetes cluster with declarative YAML configurations

plan-bound authorization architecture for governing privileged effects in untrusted computational agents.

Your site's built-in, self-hosted AI web dev. Chat to build, update, and manage your entire website. The CMS, reimagined.

TrustifAI: A Comprehensive Framework for AI Trustworthiness

Best Cursor Rules is a curated collection of 33 high-quality Cursor AI rules that actually work. Includes a Setup Wizard that analyzes your project and generates customized rules automatically.

An agentic solution designed to create a llms.txt file for any given repo or folder.

🐙 A fully-featured and well-defined generic API client to interact with @Openapi®

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

A framework to orchestrate multiple AI agents, enabling them to collaborate efficiently through smart threading, dependency management, context sharing, and distributed execution via a built-in swarm system. Built on top of smolagents, it allows the creation of an AI dream team that can scale to tackle complex tasks.

Open-source security gateway for MCP agents and tools. Inspect tool calls before execution, enforce policy, block risky operations, and emit audit-ready evidence.

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

A travel agent python app built with LangGraph using GPT model from OpenAI to be run locally or on CI/CD with Github Actions

Multi-agents operating system layer on top of Claude Code

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 lightweight, portable executable for invoking LLM with multi-API support - eliminating installation requirements while maintaining operational efficiency. 轻量级大语言模型api调用工具，无需安装，仅一个~10M可执行文件，支持自定义多种模型（OpenAI、Claude、Gemini、DeepSeek等，以及第三方提供的api）和prompt。

Dual-mode AI assistant (CLI + Telegram) powered by Perplexity AI. Fast, modular, and cross-platform.

Discord + Claude Code daemon with persistent sessions, image support, and more.

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

ChatGPT + DALL-E + WhatsApp = AI Assistant 🚀

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.

Welcome to the Document QA system! This repository contains the code for a system that allows you to ask questions about your documents and get answers based on their contents. It supports a wide range of document formats, including PDF, Word, Excel, PowerPoint, text files, and even images!

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

Streamlit Multi AI platform Claude Chat APP

Memory management for LLM Applications

PallmaAI delivers complete, lifecycle security for your AI agents, from proactive red teaming to real-time threat detection and automated remediation.

🚀 Use Claude Code CLI with Gemini, GPT-5, Grok & 20+ AI models — Multi-account load balancing, real-time dashboard, per-window model switching

🧠 Workshop Notebook and assets for the Anthropic Hackathon

A symfony chatbot Proof of concept, by using botman lib, Sonnet 3.5 Anthropic model, YoutubeV3 api and other apis.

A fast, minimal AI chat interface with support for multiple models

A Telegram bot that allows you to create your own ChatGPT in Telegram.

A Model Context Protocol server for Confluence.

Autonomous, personalized research loops for Claude Code. Set a topic, walk away, come back to a quality-gated report adapted to your projects.

This project demonstrates how to integrate a “think” tool into a LangGraph agent workflow, inspired by Anthropic’s research on structured reasoning in tool-based agents. By leveraging the “think” tool, Claude is enabled to pause and reflect on intermediate steps, improving performance in complex, policy-driven, or multi-step decision scenarios.

Anthropic api wrapper for Go

Browse, search and download AI agent skills

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.

an Advanced AI application that utilizes LLM and OpenAI for comprehensive resume analysis. It excels at summarizing the resume, evaluating strengths, identifying weaknesses, and offering personalized improvement suggestions

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"

ToxPipe: Semi-autonomous AI integration of diverse toxicological data streams

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 repository contains practical AI projects applying machine learning techniques to real-world problems.

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