Python agents

Youtube assitant using OpenAI, Langchain, and FastAPI - Using this API you can ask questions directly to your favorate podcast.

Query the ML Engineering Open Book using RAG

Simple AI search and summarising agent

An automated talent acquisition pipeline designed to streamline candidate screening using Agentic AI. This project uses LLMs to parse resumes and job descriptions, ranking candidates based on semantic alignment, with full observability provided by LangSmith.

Local-first autonomous coding agent — Claude Code style task execution, LangGraph, Ollama, zero cloud dependency

S-Chatbot is a Streamlit-based chatbot powered by GooglePalm language model. It allows users to interact with the chatbot and receive responses from the model.

Building app in databutton using LangChainAI's Constitutional Chain

AI Review Summary for Restaurants

Aora is an application designed to leverage AI for advanced document handling and natural language processing. This repository contains both backend and frontend components to get the application up and running.

This project aims to build a RAG system (chatbot & voice assistant) that responds to custom data.

A RAG LLM specialized in agricultural knowledge, currently primarily supporting soil science knowledge in China.

Aplicação Web Pessoal (SaaS) open-source. Unifica Finanças, Saúde (Bio-tracking), Produtividade e Agenda em um Dashboard de BI integrado. Construído com FastAPI, React 19 e Agentes de IA (LangGraph).

Reference materials for the Udemy course: Agentic AI Engineering on AWS

A free, self-hosted alternative to LangGraph Platform's Cron Jobs with the same API interface (compatible with langgraph-sdk).

Trigger & spectate chess games b/w different LLM agents

TOTUR is an AI-powered educational assistant designed to help users with audio transcription, PDF text extraction, and question answering. It leverages advanced AI models and Retrieval-Augmented Generation (RAG) to provide accurate and contextually relevant responses based on uploaded content.

Agentic system built with LangGraph, LangChain, Gemini 1.5 Pro, Tavily API, FPDF & Streamlit — automates deep company research, performs intelligent web crawling, and generates structured PDF reports with citations and zero manual effort.

☄️ SlackBeam is a self-hostable slack bot that helps teams generate social media content for X (formerly Twitter) directly from Slack.

working on langchains

A.U.R.A a autonomous AI robot that can sense, think, and move.

An intelligent pipeline that automates lead generation and contextual enrichment from raw CSV data. Real-time keyword filtering via SerpAPI, Contextual data tagging using Groq’s LLaMA3-powered LLM CRM-ready CSV outputs with seamless export support

QueryPilot -Production-ready multi‑agent Text-to-SQL API for Postgres. Schema‑aware LangGraph pipeline with ChromaDB + sentence‑transformers, Neon-backed DB, and full evaluation on real ecommerce & library schemas.

AI-powered deep search agents using multiple approaches - from basic web search to advanced LangChain-based research agents with adaptive strategies, multi-source validation, and intelligent synthesis capabilities.

LangChain Practice Tasks using FastAPI and LCEL

The repo hosts files for a RAG GenAI for Catalyst Center Operations, network insights

The LangChain Crash Course repository serves as a comprehensive resource for beginners who are ready to learn LangChain, a programming framework designed for creating AI agents, building RAG (Retrieval-Augmented Generation) chatbots, and automating tasks using artificial intelligence.

AG QA Application based on Brooklyn College Student Handbook 2023-2024: A semantic search and question-answering system utilizing MongoDB, Weaviate, and GPT-3.5. This application provides accurate answers to queries using the Brooklyn College Student Handbook as a data source, integrated with Gradio for an interactive user experience.

Simple telegram bot for ordering food

A AI-Based Ad Generating - Marketing Assistant.

A ReAct AI IoT vocal agent in langhchain.

Fine-tuning Qwen2.5-0.5B with QLoRA for English-to-Persian PDF translation. Built on consumer GPU (GTX 1630, 4GB VRAM).

RadioRAG: Online Retrieval-Augmented Generation for Radiology Question Answering

🚪 Governance gate for AI agents. Enforce policies before deployment: request contracts, operational safeguards, identity boundaries, action budgets. CLI tool with YAML config, JSON/text output, CI/CD integration.

Trace and debug AI agent behavior locally with a step-by-step visual tool that stores data offline for clear inspection and faster development.

A lightweight observability tool for visualizing and comparing RAG retrieval strategies. Features real-time embedding visualization and side-by-side performance metrics.

AI-driven prompt generation and evaluation system, designed to optimize the use of Language Models (LLMs) in various industries. The project consists of both frontend and backend components, facilitating prompt generation, automatic evaluation data generation, and prompt testing.

A way to apply chatgtp4 to HTB writeups using embeddings.

The AI Resume Rewriter is a powerful tool designed to assist users in optimizing their resumes by providing detailed feedback and rewriting suggestions based on Harvard's professional guidelines. This web-based application, built using Streamlit, allows users to upload their resumes in PDF format and receive actionable feedback on various sections

This project is a Medical ChatBot built using the Llama-2 model and Python, designed to provide accurate medical information. It uses a robust backend for data processing and a user-friendly frontend, leveraging technologies like Langchain, Flask, and Pinecone.

Retrieval-Augmented Generation without Vector-DB

End-to-end system for transcribing clinical audio and predicting relevant ICD-10 codes.

An AI-powered knowledge engine for NASA's space biology research, built for the NASA Space Apps Challenge 2025.

Build AI-powered document search without OpenAI bills. This RAG system uses Ollama for local LLM inference and LangChain for intelligent retrieval. Free, private, and works offline. Your data never leaves your machine.

AI agent evaluation framework for multi-participant coordination tasks. Built with LangGraph, custom MCP tools, and LLM-as-a-Judge evaluation. MSc dissertation project (University of Edinburgh, 2025).

Multi-document PDF chatbot built using Retrieval-Augmented Generation (RAG), FAISS vector search, and Groq-powered LLM for fast and accurate document querying.

Automate penetration testing tasks with an LLM-driven multi-agent framework designed for security assessment.

Zero-dependency Python helpers to normalize LangChain, MCP, Anthropic content blocks, tool results, and multimodal image payloads.

A multi-agent RAG pipeline for enterprise data with MCP integration and human-in-the-loop validation.

Learn Retrieval-Augmented Generation (RAG) from scratch by manually building chunking, embeddings, retrieval, reranking, answerability, local generation, Graph-RAG, and Self-RAG.

평일 오전 9시 뉴스 기사 중 AI 관련 기사만 필터링하여 메시지 전송하는 알림 봇

It is an AI-powered conversational interface that allows users to chat with websites.

Multi-disciplinary Project (2024)

CrewAI MCP SaaS Comparison Agents - A multi-agent system that generates data-driven B2B SaaS comparison articles using real market data, live user sentiment, and SEO intelligence

Privacy audit for multi-agent AI systems (CrewAI · LangGraph · AutoGen) — detect compositional data leaks without the central auditor ever seeing raw content.

Open-source AI agent observability. Track cost, latency, tokens, and errors for OpenClaw, Hermes, LangChain, CrewAI, LlamaIndex, OpenAI Agents, AutoGen, and Anthropic Managed Agents. Self-hosted, no cloud required.

Fast, local prompt-injection & jailbreak guardrail for LlamaIndex RAG — blocks attacks before retrieval. Powered by Bastion Prompt Protection (ONNX, ~5 ms, fully offline)

A practical guide to 6 document chunking strategies for RAG and LLM applications — Document, Fixed-Size, Recursive, Sentence, Semantic, and Agentic chunking with working code and plain-English explanations.

Phronesis is a Python framework for designing, composing, and operating AI agent systems - typed, observable, and built for production. Agents have episteme (knowledge) from the LLM; Phronesis gives them phronesis (practical wisdom).

AI-powered multi-agent stock research platform for China markets, featuring real-time analysis, debate-driven decisions, persistent memory, and localized data sources.

Advanced multi-agent orchestrator for coordinating specialized AI agents, workflows, and tool-driven automation across complex tasks.

Cognitive ARC-AGI-3 solver: 6 human-like drives, 9 reasoning modes, multi-agent architecture. Discover then solve.

Run one request through several Claude Code skills in parallel isolated subagents, then merge or judge the best answer.

Flow-state engineering arena — agents run forward simulations, listen for spectral nudges, maintain conservation in Plato's cave. Conservation spectral framework meets live agent rooms.

digital employee that lives in your terminal. It autonomously plans, researches, codes, debugs, browses the web, manages DevOps, and remembers

A self-hosted AI agent that lives on your machine, learns your daily routines, and talks to you via Telegram. Local-first, no cloud, no subscriptions.

Neural net to understand quantum computing

Production-grade multi-agent RAG workflow + an ML-infrastructure platform (PyTorch/DDP, RAG, evals, guardrails, MCP). Keyless-by-default; ships a real, reproducible Banking77 retrieval benchmark.

Local-first MCP server for shared memory, reservations, handoffs, and review evidence across AI coding agents.

Reads SEC filings from 140 technology companies, builds a live supply chain knowledge graph, and routes corporate events through 5-agent AI debate before trading

零依赖 Python AI 多 Agent 决策参考系统，把周易时位变抽象成结构化分析流程，无需 API Key 可先试玩。

🥔 Sistema multiagente local em Python com 3 níveis de performance, memória persistente e web RAG — otimizado para hardware fraco (Mac M1 8GB). Usa Ollama para LLMs locais.

BrainRegion is an AI collaboration infrastructure designed for review, consultation, planning, and memory.

Autonomous AI dev factory: sandboxed Claude Code agents design, build, review, and ship features across repos — supervised by a FastAPI PM dashboard. Experimental.

Open-source Marvis-like desktop AI agent for macOS — Main + File + Search Agents, layered dispatch protocol, mv-* card rendering, 3-tier security gate. FastAPI + Next.js. Apache 2.0.

Open Symbolic AI Core Repository

Parallel Multi-Agent AI News Analyst built with LangGraph Send API, Groq, and Tavily for real-time intelligent news briefing.

Open-source observability and control plane for AI agent ecosystems

AI-powered documentation autopilot — commit code, docs update themselves. Local-first, any LLM, section-level merging.

Cryptographic identity for AI agents: Ed25519 keypairs, DPoP request signing, delegation chains.

For3s OS - The self-hosted AI second brain that remembers, learns, and works in a team — your data, your server.

Wallstreet Tieling v0.5.0 · free open-source enterprise intelligence portal for public-data due diligence, risk discovery, and information equality

Universal MCP workspace/control-plane for AI IDEs: portable configs, skills, agents, hot-reload, and multi-tool automation.

NoWork — open-source desktop AI agent workspace for coding, research, documents, and multi-agent workflows.

Load-aware scheduling layer for multi-agent systems. Routes tokens to the highest-value work, tracks spend across every agent, and self-tunes as workloads shift. One equation, any framework.

🎮 AI 狼人杀多智能体对战系统 — 支持 7-12 人板子、LLM/Human Agent、多维评分、自进化策略系统

自进化软件质量系统 — 扫描器+修复器+DAG管道+经验积累+成本熔断

Tamper-evident memory & decision lineage for AI agents. Cryptographic proof of what your agent knew. Powered by a hybrid Python/Rust (Direct-Silicon) core.

Auditable AI agent for financial analysis — 3-phase audit pipeline with deterministic verdicts, multi-agent equity research, and versioned research memory.

Multi-Agent AI Growth System (多智能体增长系统) for Chinese medical aesthetics (医美) institutions

Multi-agent fraud detection pipeline for the Reply AI Challenge, combining deterministic transaction features, communications analysis, and a LangGraph supervisor to detect suspicious transactions with Langfuse tracing and OpenRouter-powered LLM reasoning.

Persistent graph memory architecture for multi-agent AI systems using Graphiti, FalkorDB, and MCP.

AI-powered multi-agent system for automating clinical trial analysis, evidence synthesis, and dossier generation using local inference with future Amazon Bedrock integration.

Multi-Agent OS for Claude Code — 134 agents, 15 categories, local-first routing, 14 plugins, cost-aware orchestration

Reference architecture for closed-loop AI agents — plan, execute, verify, repair.

🔨 Multi-agent task tracker for OpenClaw. Threads are tasks; @ assigns the next agent. Slack-style three-pane UI, JSONL event log, zero dependencies.

Open coordination protocol for AI agent + human teams. Inspired by agenthub.

TO BE CEO : An AI boardroom that pressure-tests startup ideas through research, debate, scoring, and replanning.成为CEO,把创业想法丢进一家 AI 公司里跑一遍：研究、部门评审、董事会结论和重规划建议。