AI Infra agents

Repositório responsável pelas demos mostradas durante o evento: MSP Tech Days 2019 @ São Paulo

A chat bot using various LLM models. It runs locally using your own GPU and/or CPU.

Build and Integrate LUIS-enabled Chatbots with Slack and Cosmos DB

An easy to use chatbot scaffold for the Facebook Messenger Platform.

Interactive reading dashboard and CLI for Kobo and Kindle — library stats, AI-powered insights, smart recommendations, book cover art, reading activity, annotation exports, and Bluesky sharing.

3-In-1-Chatbot - GPT

OllamaBot: Um assistente virtual inteligente, baseado em contêiner, capaz de interagir naturalmente em uma variedade de contextos.

Awesome-Obsidian-AI-Plugin list! You can try different AI plugins here. Also reference list for developing my own Iris system.

Repositorio responsable de las demostraciones durante el evento Caribbean Developers Conference

A productive chatbot development engine, where we can build chatbots in simple way without spend time.

A chatbot to interact with recruiters

Conversational Artificial Intelligence Interventions forEncouraging Physical Activity in Older Adults

A Library to simplify Bot Command building and Conversation definition

Simple MLX + Streamlit Chatbot

K8s-Chat is a project or chatbot :robot: with RAG function, which can answer questions related to k8s

Adaption of KoboldCPP with the goal to add missing core features

Genshin Impact Character Chat Models tuned by Lora on LLM

The Facebook / Messenger Channel Extension for Hexabot Chatbot / Agent Builder

Chatbot utilizando o conceito de Active Learning com o Bot Framework v4 e o LUIS (Microsoft Cognitive Services)

A firewall settings helper bot.

This is a Llama chat robot service. You can use it to deploy your own private services, support Llama2 series models and other open source models.

Minimalistic chatbot framework for humans.

The python client of ChatBees, Serverless Chat Platform for your knowledge base. Easily build your LLM Apps.

Framework for creating telegram bots.

LLM for Hubei Provincial Government Affairs.

System Retrieval Augmented Generation

A project written in the Rust language with the goal of offline load of small LLM Model, specifically RAG (Retrieval Augmented Generation) on mobile devices.

AI chatbots of Donald Trump and Joe Biden, fine-tuned Mistral-7B models with RAG for realistic dialogue, discourse, and policy discussions.

RolePlayAI is a cutting-edge AI-powered Telegram bot that transforms into various knowledgeable and empathetic roles, such as a doctor, lawyer, police officer, and more. Powered by OpenAI's GPT models, RolePlayAI engages users in immersive and interactive role-playing conversations tailored to their chosen role

GA + LLM hybrid framework for structured text generation and task optimization.

A RAG based LLM assistant for australian first home buyers

A fast Rust-based gateway unifying access to multiple LLM providers with logging, user control, and key-based authentication.

A minimal AI agent implementation

Prompt pull request with issues with this AutoPR quickstart template.

An attempt to create a TypeScript port of marvin from Python

Automatic embedding using mongo changestreams for Atlas Vector Search

An AI-powered brainstorming engine that multiplies and iterates on your ideas instantly.

A simple Go client for the clip-as-service server

smarter search assistant for pascal college norms 🧠

MeniAI is a CLI tool that lets developers create task-specific AI agents for automating and streamlining development tasks. These agents evolve with user feedback and can be used interactively or fully automated in CI/CD pipelines.

Build Apps for ChatGPT. ConversoKit is the open-source framework for production-ready ChatGPT Apps. Compose 19 themed widgets, 16 MCP tools, and 5 templates, and ship in under 30 minutes.

Depth-aware context compression for LLM proxies. Turn-box marker format with epistemic transparency.

Framework for Post-production Evaluation of LLM based ChatBots

Enables the application to transition seamlessly between different OpenAI models, choosing the one that is most suitable for the task described in the user's prompt.

Descubre como mejorar los modelos de lenguaje con técnicas de prompt engineering y aprovechar el poder de OpenAI para tareas de procesamiento de lenguaje natural.

A lightweight library to support the development of applications using LLMs

Fully automated LLM evaluator

Desktop ChatAI Plus 是一个高效、轻量级的桌面版AI工具，为用户提供了一个统一、便捷的界面，实现多个LLM平台的即时交互。

PaliGemma FineTuning

Front end version of an holiday management app

CreateTool-AGI is an experimental open-sorce extension of LLM that allows you to create your own Tools and automatically extend their capabilities.

A framework for creating spirals for Large Language Models finetuned for conversations.

An oversimplified UI generator for creating web pages from text prompts with Gemini and Tailwind.

⚡ Supercharge your home with AI 🧠

A .NET MAUI sample application that uses omni-input LLMs to create "My Pal", a friendly koala that insults you based on a selfie!

Waldo is a command-line AI assistant that wraps around local LLMs, Google's Gemini models and OpenAI's GPT models

Multi-agent AI framework where LLMs debate each other to verify claims. Bayesian reasoning, adversarial evidence, calibrated verdicts & full audit trails. Works with GPT-4, Claude, Gemini & local models via Ollama.

Connect and Interact with LLMs - supports Self Hosted or OpenAI

The NLU powered by LLMs that just works

Transform NotebookLM artifacts into world-class presentation blueprints. Generates tailored **Master Prompts** that guide NotebookLM to produce professional slide decks with strategic narrative structure.

Software project assistant - enter your task description and get possible task solutions.

Question answering system built with vector dbs and LLMs.

AI powered diagram generation plugin for FigJam

Extract schema, identify relationships and generate visual representation of a Firestore schema using Python, PlantUML and, optionally, an LLM or agent

永久记忆AI伴侣 · 完全本地运行 · 高度可定制

Collection of useful custom prompts for OpenAI ChatGPT [プロンプトコレ]

Automagically summarizes git commit messages using OpenAI's GPT-3 LLM.

🤖 AI-powered Git branch name generator using OpenAI and Conventional Branch naming convention. VoltAgent + Rust CLI.

Lightweight javascript library to summarize long texts using GPT model

A fun "anti-framework" for doing useful things with agents and LLMs.

The lazy engineer's salvation for prompt versioning and fine-tuning. We handle the boring stuff, you take the credit.

Production-grade event-driven AI chat platform with RAG and real-time token streaming. Built with .NET 10 microservices using Event Sourcing, CQRS, Wolverine sagas, Marten, RabbitMQ, SignalR, Keycloak, and Kong, with an Angular 21 frontend powered by NgRx SignalStore. Runs locally with Docker Compose using Ollama or OpenAI.

This is a a hands-on course teaching GenAI Foundations including Deep Learning, NLP, LLMs, Prompt Engineering, Fine Tuning, RAG, and Optimization (distillation, pruning, and quantization).

AI 智能简历分析系统，为每个职位定制专属反馈与 ATS 评分

This python utility automatically generates git commit messages using GPT3.5

Adaptive web agent that run upto 10x faster than pure LLM agents. Learns from every interaction, uses accessibility trees for stability, and plans in one shot.

Read your local files and answer your queries

AWS RAG Application Using AWS S3 Vectors and AWS Bedrock

Go pkg. for vector store

file2md is a versatile tool for converting multiple file formats to Markdown.

AI Tool RAG System: LlamaIndex-powered discovery engine for AI tools with Telegram bot interface using NeMo Guardrails

A chat bot for the Faculty of Sciences and Technologies of Tangier. Using both RAG and finetuning as separate models.

Local fine-tuning, pre-training and RAG for LLMs

RAG FAQ assistant in C# using Ollama for local AI-powered, context-aware Q&A with chat history.

A RAG built for medical queries ( in 12 hours for a hackathon )

Working demos built with SuperDoc - document RAG, AI redlining, and more.

Multimodal-VideoRAG: Using BridgeTower Embeddings and Large Vision Language Models

Solution for AI Action Summit Hackathon 2025 | Intelligent AI agent on emergency lines to assist call center operators, optimize waiting times, and provide immediate responses to urgent situations.

LilRag — A lightweight Retrieval-Augmented Generation (RAG) framework for building custom Q&A systems.

Local Embedding models benchmark tool & result

AI for Active Reading - Hackathon Winner!

This is RAG Modules Repo. This includes various modules in the RAG ecosystem.

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.

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

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

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.