GitHub agents

A basic, hackable AI code editor inspired by Cursor. Monaco + Claude + ~600 lines of JS, no build step.

Secure Docker wrapper for AI coding agents with filesystem, privilege, and network isolation

Claude Code plugin — automates the full dev cycle (spec → plan → implement → review → clean) with adaptive skill orchestration, critic loops, 12 agents, and intent-based evaluation. Zero dependencies.

The Model Context Grammar Protocol defines a simple, extensible, and non-deterministic grammar for specifying valid message types and their arrangements in exchanges with language models. This protocol enables precise, unambiguous specification of interactions including multimodal content, tool calls, and flexible message sequencing.

Unit tests for AI prompts. Catch regressions before your users do.

🤖 An AI-powered Git commit message generator.

A curated collection of production-grade Claude Skills for SEO workflows. Battle-tested skills from real agency work — distilled, cleaned, and shared back with the community.

Deploy agents using YAML and never lose the trail.

A personal Telegram bot that turns every highlight, voice note, and saved link into a commonplace book. Your data lives in a private GitHub repo you own. Voiced by orchurator — part child, part fool, part sage.

🚀 Explore modular agent skills for dynamic AI development, enabling on-demand knowledge injection through standardized `SKILL.md` packages.

A prompting framework for getting foundational models to “lazily” evaluate their reasoning trace

Local-first security scanner for AI Skill bundles. 72 rules, < 2s, zero LLM cost. Apache-2.0. SaaS at skillguard.vip

An implementation of the OmniAI interface for Anthropic.

Voodoo x Anthropic Hackathon - BI track winner (30h)

a small library around anthropic lib to enable claude function calling

A sophisticated multi-model optimization pipeline for domain-expert knowledge extraction RAG systems

GEDA (Generative Excel Data Assistant) is an intelligent Python-based assistant that uses open- and closed-source language models to interact with Excel files through natural language queries.

A cloud-native RAG (Retrieval Augmented Generation) service API built on LightRAG framework, offering plug-and-play knowledge-enhanced generation capabilities.

customizable AI chatbot that creates a personalized knowledge base from your content to provide accurate and tailored responses.

SCARF (System for Comprehensive Assessment of RAG Frameworks) is a modular evaluation framework for benchmarking deployed Retrieval Augmented Generation (RAG) applications. It offers end-to-end, black-box assessment across multiple configurations, supports automated testing with several vector databases and LLMs.

An intelligent MCP (Model Context Protocol) server that orchestrates multiple MCP servers and provides AI-enhanced workflow automation with production-ready context engine capabilities.

EdgeRAG is a lightweight Rust implementation of Retrieval-Augmented Generation focused on client-side deployment. Run complete hybrid search (BM25 + semantic) in the browser without a backend.

This repo mirrors my public Kaggle notebooks and keeps them in one clean, versioned place.

A curated collection of Spring Boot projects demonstrating AI and LLM integrations, including examples of AI-powered applications, multi-provider LLM setups, and best practices for Spring AI, modular design, and integration testing.

A photorealistic Japanese VR museum featuring ukiyo-e artworks with a RAG-powered local AI guide that can hear and speak to visitors. Non-invasive visitor behaviour tracking and analytics for exhibition optimization. Privacy-first, runs fully offline. Built with Unity intigrating technologies like Ollama LLMs, RAG, Whisper, Powershell TTS and more!

Multi-agent RAG research assistant with FastAPI, React, FAISS, Redis memory, async agents, streaming, sources, and evaluation.

🚀 Explore Happy-LLM, a tool designed to enhance interactions with language models, offering a user-friendly experience in Chinese.

Faiss with sqlite

Haven is a privacy-first vector database and RAG platform for browsers. Full semantic search, embeddings, and LLM inference—all client-side.

Glaucias is an open source platform focused on RAG. The purpose of the platform is to extract the structure of documents and make it as feasible as possible for RAG by identifying the references in the text(implicit and explicit)

Automate your customer support using Retrieval Augmented Generation (RAG): OpenAI + Pinecone

Projects Implemented for the Udacity Generative AI Engineer Nanodegree Program

This project leverages the Phi3 model and ChromaDB to create a Retrieval-Augmented Generation (RAG) application.

ZeroPal: A concise RAG example for LightZero QA.

A plugin dveloped for ChesireCat AI to detect complex math formulas from any image and reproduce them in Latex syntax

search images with words!

A comprehensive, containerized Second Brain Database built with FastAPI, MongoDB, and Redis. Features advanced RAG, family management, and micro-frontend architecture.

All code to get your own RAG functional

Azure AI Apps - RAG, Agents, and Chat applications using Azure AI Foundry, Azure Kubernetes Service and other Azure AI related services.

The Real Time Social Media Content Retrieval System fetches real-time LinkedIn posts based on user queries, offering multiple post retrieval and customization options. Although initially focused on LinkedIn, it can be expanded to incorporate other social media platforms, facilitating cross-channel post similarity searches.

结合检索以及LLM进行问答

💬 An AI-powered backend system that lets you query your MongoDB data in natural language using Gemini, Pinecone, and Groq. ⚡ Powered by RAG (Retrieval-Augmented Generation) to fetch, understand, and respond intelligently from your own database.

A cross-platform command-line utility that creates projects for generative AI RAG application development from cookiecutters (project templates), e.g. Python package projects, C projects.

A service for automating document ingestion for Semantic Kernel's KernelMemory service

simple rag with c#

extractor is an HTTP service used to convert PDF, Markdown, HTML, Docx, Xlsx, CSV and other files into plain text output. It is used in RAG implementation to read external documents for vectorization.

AI-powered browser-based vulnerability scanner using UniXcoder embeddings and RAG with LLM to detect security flaws across 9 languages.

A self-hostable RAG search engine - One-click on Vercel

Welcome 👋 to the WetroCloud SDK! This SDK enables seamless integration with the WetroCloud API, making it easy to manage collections, handle resources, and leverage AI-powered queries, including Retrieval Augmented Generation (RAG).

KG1 is a social knowledge management application, infused with AI.

A production-ready RAG (Retrieval-Augmented Generation) API built with .NET 8. Upload documents, ask questions, and get AI-powered answers with source citations and streaming support.

Persistent AI memory that follows you across every tool, session, and interface. Fully local.

From the Roots to the Fruits !

A Local Retrieval Augmented Generation application that aims to compete with NotebookLM.

🤖GraphRAG v2 API (From Local to Global: arxiv.org/abs/2404.16130) Playground 🥦

A PoC of using Weaviate + DSPy to make a BookStore CoPilot

Flare AI Kit template for Retrieval-Augmented Generation (RAG) ☀️

Cutting-edge tool designed to intelligently segment text documents into optimally-sized chunks

Hexa est un robot open source en phase de développement. Son objectif est d'aider dans l'initiation à la robotique. Il sera équipé d'un système d'intelligence artificielle pour la communication, la gestion des animations ( cinématique inversée ), l'adaptabilité à son environnement.

AI-powered document query system using LangChain, ChromaDB, and OpenAI for efficient RAG-based information retrieval.

REST API for computing cross-modal similarity between images and text using the ColPaLI vision-language model

The Zoomcamp LLM Course focuses on tools for working with LLMs and RAG, including OpenAI API, HuggingFace, Elasticsearch, and Streamlit. It covers vector search, embedding creation, data ingestion with Mage, and monitoring using Grafana, emphasizing practical applications and best practices.

This project demonstrates a real-time AI "Meeting Coach" showcasing the use of Confluent Cloud for Apache Flink AI Inference functions to build a real-time Retrieval-Augmented Generation (RAG) pipeline. The demo uses both a static knowledge base of sales documents and real-time simulated meeting data.

Extract the content while preserving the layout, images, and tables. Perform a full bilingual AI translation of the PDF document, ensuring precise segmentation of sentences and paragraph boundaries to enhance translation quality./提取内容后保留排版，图片和表格的 PDF 文档全文双语AI翻译，精准切分句子和段落边界，提升翻译效果

Semantic search engine for the French Bible.

An MCP server that uses LightRAG and Tree-sitter to build a repository knowledge graph from code and docs, for Q&A and implementation planning.

Generate briefs based on financially relevant information from Bigdata.com

Proyek Ollama DeepSeek Llama RAG (Retrieval-Augmented Generation) - Fine-Tuned Proyek ini bertujuan untuk membuat sebuah Generative AI yang dapat membuat sebuah module ajar yang dapat digunakan oleh guru untuk mengajar siswa.

An Agentic workflow to equip Robots with memory

A RAG based Chatbot for the Electron Ion Collider

a barebones implementation of an ExpressJS server with RAG pipeline without using LangChain or any other LLM Framework, with features for calling LLMs, data processing, etc built from scratch

AI-powered agent that lets you query and analyze your database using natural language

A RAG system designed for law firms to enable lawyers to efficiently "talk to their data"

Learn to build AI agents step-by-step with simplicity using Mastra, and deploy them easily on Mastra Cloud

Golang RAG chatbot for university admissions. Built with LangChain, pgvector, Neo4j & Gemini AI. Features semantic search, knowledge graphs, async processing & hexagonal architecture. Demonstrates high-performance AI in Go as alternative to Python RAG systems.

Structured marketing knowledge base optimized for AI, LLMs, agents, and prompt workflows. Modular, reusable, and high-density content for sales, marketing, and copywriting.

A microservices-based RAG platform that supports multi-format document parsing, semantic search, and conversational AI, powered by Google AI and Qdrant.

Different retrieval techniques implemented in Haystack - presented at PyCon Lithuania 2025 🇱🇹

Self-hosted RAG for your AI with GUI, REST API, and MCP support. Based on pgvector.

Open Source Amazon Rufus inspired RAG chat over customer reviews

KnowFlow is a hybrid Retrieval-Augmented Generation (RAG) system combining semantic search with knowledge graph reasoning for intelligent document processing and querying.

Repo for PyCon Colombia 2024.

A self-hosted, privacy-focused RAG (Retrieval-Augmented Generation) interface for intelligent document interaction. Turn any document into a knowledge base you can chat with.

A CLI tool for managing LLM conversation trees

Open-source library of AI superpowers — 59 skills, 34 commands, 10 agents + 24 GSD subagents, 3 system bundles. An entire team, wherever your AI lives. Vendor-neutral across Claude Code, Cursor, Codex, and any AGENTS.md tool.

A collection of tools to supercharge trading strategy development on the Blueshift platform.

Persuades your LLM to output schema conforming JSON. Prompts for N retries until schema is matched. Provides error context in retries. Persists sessions, enabling front-loading initial context. Zod for schema and error definition.

Code Guardian enforces architectural rules in your codebase, especially valuable when working with AI-generated code. It validates changes against your defined standards to prevent violations and reduce AI hallucinations.

A Tool that Allows You Run PyTest within Jupyter Notebook Cells

UI frontend for loopgpt self-prompting autonomous AI agent, to aid in debugging initial prompts

Yassir — open-source AI research agent for halal finance and Shariah-compliant investing

A self-evolving coding agent written in Go. Reads its own source, decides what to improve, writes code, runs tests, and commits — autonomously.

Give AI agents your real Chrome browser — fully autonomous, no manual tab clicking. Works with OpenClaw, Claude, and any MCP agent.

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.

The agent eval standard for MCP — score output quality, catch safety failures, enforce cost budgets

ACI (Agent-Computer Interface) — The open standard that turns any application into a structured, agent-operable interface. One protocol. Any software. No screenshots.

AI Coding Assistant powered by MCP server : it reads your code locally to provide truly context-aware help, explanations, and suggestions directly related to your files. Code smarter, locally or using external API..

The universal AI agent platform. Scaffold, configure, guard, and deploy AI agents across 7 frameworks — OpenAI, Anthropic, CrewAI, LangGraph, Google ADK, LlamaIndex, AutoGen. One command. Any model. Deploy anywhere.