Python agents

Slack App Bot that calls ChatGPT using Python

AI dynamically generated examples for simple anki cards

A Generative AI App using advanced RAG techniques to answer questions from a Resume.

This project is a Python application that provides an interface for interacting with the GitHub API. The project structure is organized into modules that make it easier to maintain and expand its functionality.

Track insider trades and political stock transactions in real-time. Monitor SEC filings, analyze patterns, and get AI-powered insights on market-moving trades.

Financial Analyst | Assistant AI.

This repository contains the source code for a Text-to-Speech (TTS) web application powered by OpenAI's text-to-speech API and Gradio. The application is designed to convert user-input text into spoken audio using a selection of AI-generated voices.

Embeds your codebase into a local vector database and exposes it as an MCP tool for fast semantic code search.

This project is dedicated to building an intelligent data processing pipeline using AutoChain LLM and BERT ML.

This is the repository for a Streamlit application that helps with job applications. This app integrates OpenAI LLMs for building tailored resume and cover letter for a Job description.

GPT Retrieval-Augmented Generation

LYMT: Let Your Model Think

Distributed rate limiter for LLM APIs with FIFO queues, TPM/RPM limits, and burst prevention

Cloud Automated Telegram ChatGPT Bot

Chat with local Wikipedia embeddings 📚

AI Code in less than 100 lines. Open source, beginner-friendly, production-ready.

在终端中一键切换并管理 Claude Code、Codex CLI、Gemini CLI、OpenCode、OpenClaw 的 provider 与 API Key，适合服务器、CI/CD 等无 GUI 环境

Turn your repetitive Claude Code workflows into reusable skills — automatically. Zero config, zero dependencies.

AI-powered toolkit for Claude Code that provides structured workflows, commands, and agents to automate planning, coding, testing, and shipping software.

🔍 Benchmark jailbreak resilience in LLMs with JailBench for clear insights and improved model defenses against jailbreak attempts.

A minimal Python tool to monitor multiple log files simultaneously in a single terminal window via tail. With Claude Code integration to automatically discover relevant log files from your recent experiments.

🧠 Chat with LLMs from your terminal

Describe any task in natural language — OmniDrive analyzes intent, installs dependencies, and executes automatically.

Python Framework for AI Usage - Tackleberry (or TB) is helping you tackle the access to AI

YouTube Thumbnail Generator with AI-powered face detection and image generation

MCP server for AI-powered travel search — flights, hotels, weather as MCP tools with MongoDB-backed per-tool TTL caching tuned to each upstream API. Architecture: tanayshah.dev/projects/travel-mcp-server

MCP server that gives LLMs web search, intelligent article extraction, PDF parsing, and contextual awareness (datetime/geolocation) - zero setup, no API keys.

MCP server that lets Claude Desktop and Claude Code pass messages without copy-paste

Hand off your Claude Code session from terminal to phone (and back) without losing context

🤖 Assistant d'écriture alimenté par l'IA - Corrigez, traduisez et améliorez vos textes instantanément avec Gemini, Claude et GPT. Simple, rapide et respectueux de votre vie privée.

A complete, weekly-operable system covering research findings, funnel design, networking workflows, application protocols, AI automation, templates, and a 30-day launch plan. No spam. No fake experience. High-conversion by design.

🪂 Latency-aware model cascade for agentic LLM workflows. Auto-switches to a faster model when yours is slow.

A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows | Claude Skills 精选列表：定制 Claude AI 工作流的技能、资源和工具合集

Multi-session orchestration for Claude Code. Monitor, auto-approve, block, and send tasks across terminals.

AI-powered WSQ courseware generation platform built with Claude Agent SDK and Streamlit. Automates creation of Assessment Plans, Facilitator Guides, Learner Guides, Lesson Plans, Assessments, Slides, and Brochures for Singapore training providers.

Find the MCP schema issues eating your context window. 156 checks. Grade A+ through F. ESLint for MCP.

AI-powered QA & security analysis CLI for any stack — scans web apps, source code, and APIs for vulnerabilities, quality issues, and performance problems. Powered by GPT, Claude, or Gemini.

MediTech is an innovative AI-driven Electronic Medical Record (EMR) system designed to streamline and enhance clinical documentation for medical professionals.

Role-based AI marketing copilot for Claude Code. Clone, run /start-copilot, and the wizard fetches your site, builds your brand doctrine, wires your tools, and hands you a ready-to-use copilot. Sonnet 4.6.

A panel of AI personas that debate your decisions inside Claude Code. 3 rounds, one user-centric synthesis, full debate recorded to a markdown file.

Production-grade, multi-tenant chat service with FastAPI + WebSockets, OpenAI/Anthropic orchestration, semantic caching, and K8s/IaC deployment, Includes observability (Prometheus/Grafana/Jaeger), FinOps cost tracking, and DR runbooks.

Tiered memory for AI — episodes, facts, preferences, reflections. Local. Portable. Yours.

An MCP server to interact with Strava

Enhance the LinkedIn user experience with AI

🐍 Django-native AI SDK — agents, tool calling, streaming, 12+ providers

A terminal-native, multi-provider intelligent assistant that plans, executes, and tracks developer tasks, not just answers prompts, similar to Claude Code and Gemini CLI.

Universal Python library for Structured Outputs with any LLM provider

Your own AI radio station, native to Home Assistant. Two Italian hosts who riff on what your home is actually doing.

AI-powered firewall log analysis platform. Upload Cloudflare/nginx/Apache logs, get OWASP-categorized threat reports with PDF export.

AI-powered documentation RAG system with MCP server for Claude Code. Search and retrieve technical documentation on-demand with vector embeddings and smart web scraping.

An AI-powered document assistant with multi-model retrieval system

Demo of uv for a streamlined Python package management experience

A Retrieval-Augmented Generation (RAG) based multilingual chatbot specialized in nutrition & diet planning. It combines powerful NLP models with a curated nutrition knowledge base to provide personalized diet recommendations, meal plans, and fitness tips based on user input (age, weight, activity level, health goals, dietary preferences).

Smart Search with GenAI is an AI-powered semantic search tool that delivers context-aware, summarized answers to natural language queries over structured data. It leverages Streamlit, FAISS, and Azure OpenAI for efficient vector search and LLM-based summarization.

Self-evolving RAG that automatically adapts knowledge base using evolutionary algorithms

AI academic assistant for UofT students — grade calculator, syllabus parsing, and natural language chat

A Medical RAG based chatbot built using llama2 model🦙.

An entire RAG (Retrieval-Augmented Generation) pipeline library designed to streamline the integration of language models with retrieval systems. ragyphi can extract text, table and image data from your pdf files and uses clever llm-based summarization techniques to augment the extracted data for efficient retrieval.

A Retrieval-Augmented Generation (RAG) system designed to provide answers from the arabic datasets. This project is done on static news archives using RESTful API and a web UI.

An intelligent chatbot that answers questions about your CV using Retrieval Augmented Generation (RAG)

CPU-only RAG stack: PDFs→Docling→Ollama→pgvector. Windows/macOS/Linux. Docker Compose. Graph-aware code search + scanned PDF OCR.

Medical-QA-Chatbot-Using-PySpur-RAG-and-LLMs

A CLI that takes natural language and converts it to bash commands using a local code generation model or a curated prompt-based rule engine.

Pure-Python, zero-dependency RAG memory engine for conversational AI. Retrieves semantically relevant messages from conversation history using two-phase retrieval, TF-IDF + concept-overlap scoring, narrative element extraction, and bidirectional typo correction. No embeddings or vector DB required.

httpie for embeddings. Embed text, images, audio, video, and PDFs from the command line.

A runtime governance, security and execution control layer for Retrieval-Augmented Generation (RAG) systems

An Agentic RAG-powered chatbot delivering intelligent, fact-grounded and context-aware answers for the DIEM Department at the University of Salerno.

A repository for the "NLP with Transformers" course project at Heidelberg University.

A genral RAG Search chatbot, with SoTA RAG techniques such as HyDE, Hybrid retrieval with BM25 + RRF and Cross encoder reranking. Evaluated on the BEIR scifact dataset and compared all the different pipelines i tried along the way

Published PyPI package for ArXiv embedding benchmarks, retrieval evaluation, and scientific RAG experiments.

Open-source machine-readable standard for pharmaceutical SOPs - deterministic, auditable, GxP-aligned

implemented vector similarity algorithms to understand their inner workings, used local embeddding models

API-difycall 是一个轻量级的 Python 项目，用于简化与 Dify API 的交互。Dify 是一个强大的 AI 应用开发平台，本库旨在让开发者能够更便捷地集成和使用 Dify 的各项功能。

Prompt-safety guards as a Python library. TF-IDF, RAG, LLM as a judge pipeline

💬 Engage in continuous chat while dynamically building a JSONL playbook, enhancing insights and strategies with each interaction.

Simple tool for RAG (Retrieval Augmented Generation) applications to be run over locally stored files

This RAG Streamlit app lets users chat with PDF documents using Gemini and Google's generative AI. Upload PDFs, process text, and get intelligent answers to your questions.

The AI-Based Pre-Screening Assistant Bot is an AI-powered technical interview assistant that evaluates candidates using adaptive questioning, real-time feedback, and automated report generation. Built with Streamlit and RAGPipeline, it dynamically adjusts question complexity, tracks candidate performance, and emails interview summaries

EarningsAI Demo is a powerful tool that combines audio transcription, document processing, and AI-powered analysis to help users extract insights from earnings calls and financial documents. Built with Fireworks AI and MongoDB, it provides both a command-line interface and a web application for processing and querying financial data.

RAG agent with SGR, smart indexing and reranking, metadata enrichment, parent document extraction

BigQuery Semantic Search Orchestrator

MCP server for enhancing knowledge base search and retrieval

RAGent Chatbot is a smart AI assistant that combines Retrieval-Augmented Generation (RAG) with a tool-using LLM agent. It can answer user queries using uploaded documents, perform web searches, summarize text, solve math expressions, check weather, and more — all powered by LangChain, Qdrant, and Gemini.

The document normalization engine RAG has always needed. Parse any document, understand its structure, build RAG that actually works.

RAG-optimized documentation and data sources for AI-native development on the Flow network. Ground LLMs in accurate Flow and Cadence context.

A small reranker service using mixedbread.ai reranker model

A project to show good CLI practices with a fully fledged RAG system.

RAG (Retrieval-Augmented Generation) and vector search to transform plain questions into SQL queries, enabling effortless, intelligent conversations with your SQL database.

RAG code sorting search, RAG knowledge organization

Implementation of Retrieval Augmented Generation RAG-based LLM from html web pages

A comprehensive evaluation toolkit for assessing Retrieval-Augmented Generation (RAG) outputs using linguistic, semantic, and fairness metrics

A local RAG pipeline for the Hollow Knight wiki - chat with wiki knowledge using Ollama and Supabase.

🚀 A powerful Model Context Protocol (MCP) server powered by Gemini Embedding 2. Transforms any local directory into an ultrafast, visually-aware spatial search engine for AI agents! 🔎✨

Retrieval Pivot Attacks in Hybrid RAG (Vector → Graph)

*Built upon the integration of text, image, and audio modalities, this Multi-modal RAG task follows a structured, step-by-step pipeline to effectively combine and process diverse data sources.*

RAG - Ops: RAG with Operations. We help you to deploy RAG with changing in datasources.

A CLI RAG app for digging through the JFK files.

A quick and simple example for build RAG using LangChain related tools

A system that combines Retrieval-Augmented Generation (RAG), the Claude Sonet 3.5 LLM, and the Pathway framework to analyze financial reports and tables. It ingests data from Google Drive, processes both structured and unstructured formats in real time, and presents insights via a Streamlit-powered interface.

LLM Chatbot-RAG by OpenVINO. The chatbot can read a PDF file and answer to the related questions.