Custom agents

Course material for the DSD bootcamp on combining large language models with vector databases.

RAG based QA system based on domain knowledge from local PDFs, useful for reviewing for exams and interviews :)

Open-source AI Plant detection that provides fast and accurate response.

Implement a Retrieval-Augmented Generation (RAG) workflow using Vertex AI RAG Engine and Gemini 2.0 Flash on Google Cloud.

A LangGraph-powered fantasy RPG engine that builds an agentic world while utilizing tool-calling, retrieval-augmented generation (RAG), and dynamic summarization for efficient token usage. Players interact with evolving storylines, NPCs, inventory, and game logic through a language model acting as the game master.

知识库RAG项目

A Retrieval-Augmented Generation (RAG) chatbot built in Python using embeddings, PostgreSQL with pgvector, and Hugging Face language models. This project allows a chatbot to answer user queries by retrieving relevant information from a corpus of text documents.

Local AI memory system for Node.js — verbatim storage, semantic search, knowledge graph, MCP server. Port of the Python MemPalace.

🧠 Local-first RAG index that watches your files and serves MCP semantic search

A curated collection of papers, frameworks, tools, and resources on Retrieval-Augmented Generation (RAG). Maintained for students of the Text Mining and Data Visualization course as a starting point for thesis research.

Lets you ask question about topics in video and gives summary of the YouTube video.

Chat with your database. Locally. VS Code extension for exploring and understanding schemas and stored procedures using local LLMs. SQL Server · PostgreSQL · MySQL. Zero cloud dependency.

A graph-first, embedded multi-model database engine

LearnAbility is a comprehensive learning platform designed to provide an accessible, personalized, and inclusive educational experience for all users—especially underserved communities and students with disabilities.

Demo showing how the Trustworthy Language Model add reliability to LLM outputs and improves RAG, agents, and data enrichment worfklows. can be used to improve fine-tuning of LLMs, accuracy of LLM outputs, and smart routing for RAG and agents.

Nancy's RAG backend and HTTP API/MCP server connectors.

AI RAG that teaches you what is going on in Ghana's parliament

Multimodal emotion assistant with visual emotion analysis, Qwen realtime voice interaction, and local RAG knowledge base.

Starter project for creating an API endpoint that performs web searches, scrapes results, and generates answers using LLM.

RAG with LLM agents for SQL & graph databases

A vanilla from scratch Retrieval Augmented Generation (RAG) implementation that includes a web interface to control it.

🧠 [ACM-TORS] A Resource for Multi-Modal Learning in Visual RAGs

Memory module for LLMs and Agents with MCP

A FastMCP based mcp server for weaviate, deployable using uvx.

RATE: An LLM-Powered Retrieval Augmented Generation Technology-Extraction Pipeline

POMA AI cli - integrate poma into your pipeline. Optimised for agent use.

My first Multi-Modal RAG pipeline....Dummy version

Analyzing the performance of Mamba-based vs. Transformer-based Retrieval Augmented Language Models over increasing k number of chunks retrieved.

Autonomous multi-agent framework for self-correcting image synthesis using 'Think → Generate → Critique → Refine' cycles with Gemini 3.1 and SDXL.

Root Cause Analysis of Task Plans implemented using BehaviorTrees using ChatGPT

Allows you to merge search results from multiple search engines using the reciprocal rank fusion algorithm.

A Retrieval-Augmented Generation (RAG) system for automating Security Operations Center (SOC) log analysis. This project combines NLP techniques with vector search to process security logs, enabling semantic querying and visualization through an interactive Streamlit interface.

CodeMap is a CLI tool that generates optimized markdown docs and streamline Git workflows.

针对有旅行意愿，但是没有时间规划行程，或在旅途中想要获得帮助建议等问题，开发了一个基于Spring AI框架的智能旅游咨询平台。项目采用RAG检索增强生成技术构建专业知识库，通过Tool Calling、MCP协议集成多种外部工具服务，实现具备自主规划能力的AI Agent智能体，为用户提供旅行方面困惑的咨询服务。

Hardware-Accelerated Cryptographic RAG System — GPU simulation of SHA-256 hash engine with AES-256-GCM encryption and Merkle tree integrity. NOT real ASIC hardware.

Generalized, Offline-First Multimodal AI System

NLP (Natural Language Processing)

A Visual and Interactive tool to learn and explore Hybrid RAG (Vector + Graph DBs) and Agentic RAG systems.

A production-quality real-time messaging app built with React Native (Expo), Cloudflare Workers, and Durable Objects, featuring edge-native AI capabilities with RAG and multi-step agents.

My personal notes, code and projects of the Udacity Generative AI Nanodegree.

A library to calculate similarity scores between two collections of text sequences encoded using transformer models for bitext mining, dense retrieval, retrieval-based classification, and retrieval-augmented generation (RAG).

A fully offline NLP pipeline for extracting, chunking, embedding, querying, summarizing, and translating research documents using local LLMs. Inspired by the fictional mystery of Dr. X, the system supports multi-format files, local RAG-based Q&A, Arabic translation, and ROUGE-based summarization — all without cloud dependencies.

This project demonstrates a production-ready RAG application for Alfresco using Spring AI.

Self-Reflective Question Answering for Biomedical Reasoning

All things Essential For my Learning Curve in LLM

The CMR system is a sophisticated memory-enhanced language model architecture that enables contextual memory reweaving for improved performance on long-context tasks.

Versatile LLM Tool Use (Function Calling) package for Laravel, compatible with all LLMs, enabling LLM to execute actual code functions (unlike LLMs' built-in capabilities).

AI search and chat for the LessWrong forum

Chat with your GitHub repository using RAG and Elasticsearch as a Vector Database

LLM with RAG example for querying URLs or PDFs with Ollama and Gradio/Flask

Mimicking Apple Intelligence, this project enables on-device Retrieval-Augmented Generation across all your Apple devices with zero cloud dependence.

A Retrieval-Augmented Generation (RAG) system using Vector and Graph Database

Local-first cognitive memory runtime for AI agents

RAG implentation in Golang with Milvus DB as example.

RAG tool by Gemini File Search

learning generative models

RAG-Enhanced-NCERT-Tutor is an AI-powered tutor for NCERT curriculum, using Retrieval-Augmented Generation (RAG) to provide accurate and contextually relevant answers. It integrates retrieval techniques with a language model to enhance learning by offering detailed explanations and resources based on real-time queries from NCERT materials.

The only prototyping Multi-Agent systems repo you will need, running on dockers

Full featured aggregation of all your AI agents in single vector database for full MCP search.

Benchmark LLMs for your RAG system - Compare Gemini, GPT, Claude & local models (Llama, Mistral, Qwen, Phi) via Ollama with advanced performance metrics.

C# SDK for the Jina API -- embeddings, reranking, and search

This repo houses experimental projects inspired by insights from the course 'Building and Evaluating Advanced RAG Applications' offered by DeepLearning.AI

Enhance SQL query generation using OCI Gen AI and Marqo. This project integrates with Oracle Autonomous Data Warehouse, leveraging DDL and comments for context-aware natural language queries, indexing and searching vectors, and executing optimized SQL commands.

VPHO is a RAG methodology that allows LLMs to be context-aware and easily navigate large volumes of chat logs and email logs.

Production-ready support ticket classification using Unity Catalog AI Functions, Vector Search, and RAG. Features 6-phase workflow, knowledge base integration, and Streamlit dashboard.

MCP server for intelligent paper/PDF management with RAG capabilities

The project shows a managed RAG service based on Knowledge Base.

Kubernetes operator for declarative AI workflows. Model pipelines as CRDs (Stories, Engrams, Impulses) with real‑time streaming and batch execution.

Building a RAG System connected to Confluence using Airflow, FastAPI and Qdrant

An interactive tool for exploring and comparing 5 different document re-ranking techniques with real-time evaluation and visualization to improve the accuracy of RAG System.

LexiFIR is a mobile app built to aid the Madhya Pradesh Police by addressing the lack of legal expertise. Featuring a conversational chatbot, it assists in investigations, collecting evidence, providing landmark court judgments, legal training and analyzing crime patterns across India, enhancing law enforcement and efficiency.

🤔 wondering if your chunks are good? 🦉 Judie is here to Judge and Evaluate your Chunks! ✨

A JS port of llmcord, with additional features.

AI Alliance Living Guide to Applying AI

Investigating the vulnerability of Large Language Models (LLMs) to misinformation in Retrieval-Augmented Generation (RAG) systems by poisoning vector databases and analyzing LLM responses to identify potential weaknesses and exploitation risks.

Official dataset and code for "SyllabusQA: A Course Logistics Question Answering Dataset" (ACL 2024)

Implementation of Hierarchical Patch Compression for ColPali: Efficient Multi-Vector Document Retrieval with Dynamic Pruning and Quantization

Copying LLM chat conversations as clean PDFs, Quarto Markdown or full HTML. Currently supporting ChatGPT, Claude, Gemini.

MCP server providing tools to access EFSA's comprehensive OpenFoodTox Chemical Hazards in food dataset

Production-grade LinkedIn CLI for humans and LLM agents

GNME (pronounced Gen-Me) is a lightweight framework that replaces static, task-based specifications with living Module Genomes. It is designed specifically for developers using AI assistants (Cursor, Claude) to build complex, evolving systems.

Browser-based Claude-Code-style agent harness for local uncensored Ollama models. MoE-fast, security-audit aware, MIT.

Spora is the lightest OSS AI Gateway. This product is managed by the startup Fisarum.

Open-source, self-hosted chat server for humans and AI agents, with OpenClaw, Hermes, and Nanobot channels.

A fully autonomous, self-reliant AI agent performing Base trading on the Limitless

Give AI Agents a "body" with TCM Five Elements logic. Simulates biological feedback loops, organ interactions, and persistent emotional states for LLMs. 基于中医五行理论的智能体持久化情感系统。

The self-healing AI scraping agent

Production-ready template for AI agent workflows with Hermes Agent, Temporal durable orchestration, and human-in-the-loop review. Ships with an exam grading demo.

Pure-Python toolkit for inspecting, editing, converting, and analyzing 3D print files, supports 3MF, STL, OBJ, PLY, and GLB. Detects source software (Bambu, Orca, Prusa, Cura, Fusion 360, etc.), checks compatibility across 15 CAD and slicer programs, and works with any AI coding agent (Claude, Cursor, ChatGPT, Manus). Zero dependencies beyond numpy

Secure MySQL MCP Server with Clean Architecture. Enables AI assistants (Cursor, Copilot, Cline) to safely interact with MySQL/MariaDB databases, featuring RBAC, audit logging, and intelligent query validation.

Transform Your AI Models into Tradeable Digital Assets. Mintable AI Agents is a revolutionary platform that bridges artificial intelligence and blockchain technology, enabling you to tokenize your AI models as NFTs. Own, trade, and verify AI agents like never before.

MSA Project

Desktop app to discover, install, and manage MCP servers across Claude Desktop, Cursor, Windsurf, and any AI client. One-click setup for 3,400+ Model Context Protocol servers. Built with Tauri + Vue.

A plug-and-play framework for AI-assisted software development, enhancing context-aware collaboration in complex codebases. Perfect for tools like GitHub Copilot. 🐙✨

Pefectly integrate CapSolver with OpenClaw to enable automatic CAPTCHA bypass for AI agents during web automation tasks.

Claude Skill for querying and exporting WeChat 4.x chat history — DB schema, SQL templates, and LLM export format built on top of ylytdeng/wechat-decrypt.

Cross-Axis Analysis Framework | 横纵分析法 - 通过纵向时间深度 + 横向竞争格局的交汇分析，快速建立系统性认知

Universal security scanning skill for AI agents - finds hardcoded secrets, API keys, and vulnerabilities in any codebase. 60 regex rules (46 GitLeaks-informed secret patterns, 14 OWASP Top 10 checks) plus 15 dangerous-file checks. Markdown/SARIF/JSON reports. Works across Claude Code, Cursor, Windsurf, and any agentic platform.