Python agents

fastapi backend powered by crewai agents for automated research, data retrieval, and synthesis. orchestrates multi-agent workflows for query analysis, information gathering, and summarization.

🤖 Define and execute multi-agent AI workflows declaratively using YAML, simplifying orchestration and enhancing collaboration through automatic context handling.

用大语言模型（LLM）构建agent。

The Lobbying Crew is an AI-powered tool designed to streamline and automate the lobbying process.

Migrated → github.com/zistica/korveo (rebranded). Archived.

A web-based AI agent that generates personalized JEE preparation roadmaps based on a student's current standard, percentage and goals.

Hierarchical Multi-Agent System for Top 5 US Stock Selection

Portfolio showcasing four implementations of an AI agent team task using different frameworks (No Framework, Agency Swarm, CrewAI, and LangGraph). Compare approaches to agent coordination, from basic patterns to complex workflows, all built with Cursor's Agent feature.

Multi-agent AI system using crewAI to automate LinkedIn profile data extraction and analysis.

A lightweight framework for running structured debates with AI agents using the CrewAI library. In a nutshell, you define two “debater” agents (pro/con) and a “judge” agent, wire them together in a Crew, then kick off a debate on any motion.

Open-source observability platform for AI agents. Trace every LLM call, tool use, and decision in real-time. Supports OpenAI, Anthropic, Gemini, LangChain, CrewAI, LiteLLM, MCP. Self-hosted. Zero dependencies.

TheBlend.ai Website code that create blog content using AI

AI agent crew that generates institutional-grade crypto market intelligence reports with real-time data from CoinGecko, Binance, SEC EDGAR, FRED and more using CrewAI + 15 MCP servers + Google Gemini.

A Flask-based multi-agent system powered by CrewAI, combining food recommendations, vector search from S3, and conversational intelligence.

Open-source multi-agent AI think tank platform. Collaborate, research, and generate insights with AI agents. Results stored in Notion and Markdown. Web search enabled.

An intelligent business automation system powered by CrewAI

Easily create and run AI Agents through simple configuration that is based on Crew AI.

This project uses CrewAI agents to automatically convert YouTube videos into high-quality blog articles. By combining intelligent task delegation, tool integration, and multi-agent collaboration, the system streamlines the process of researching and writing blog posts from video content.

An intelligent multi-agent system that automatically generates comprehensive documentation for GitHub repositories using CrewAI's collaborative agent framework.

LifeOps AI v2.0: A cyberpunk-inspired personal productivity suite powered by Multi-Agent AI (CrewAI). Optimize your Health, Finance, and Studies through a unified intelligent command center.

An AI agent which surfs the internet, gathering information about a topic provided and then provides a .md file containing a blog about the same.

A post generator powered by CrewAI with Gemini 1.5 Flash & Groq Cloud (deepseek-r1 Distill Llama 70b)

CrewAI AgentOps: Monitor your AI Agents

A modular, AI-driven research and reporting framework built on Crew.ai. Define agents and tasks via simple YAML configs, then spin up a “crew” of LLM-powered specialists to research, analyze, and generate professional reports on any company or topic.

Runtime authorization layer for AI agents. Every action is ALLOW, DENY, or REQUIRE_APPROVAL before it hits the real world.

Payment infrastructure for AI agents. One line to send money between machines. USDC/ETH on Base L2.

A demonstration project showing how to orchestrate a multi-agent “engineering team” using the crewai framework. This repo defines a crew of specialized agents (engineering lead, backend engineer, frontend engineer, test engineer) and a set of tasks (design, code, frontend, test) which are executed sequentially to satisfy a simple account-management

Anyparser Python SDK for RAG/ETL Pipelines - File Content Extraction. Supports extraction from various file formats including PDF, Microsoft Office documents, OCR/Image to Text, Audio to Text, and Website to Text.

A demonstration of using the CrewAI framework to automatically plan, write, execute, and collect output from Python coding assignments using an LLM-based “Coder” agent.

A demonstration of CrewAI framework capabilities through an autonomous trip planning assistant that recommends destinations, gathers city details, and generates comprehensive travel itineraries based on country and season input.

This GitHub repository, "Meeting-Prep-Using-CrewAI", is a project that aims to utilizeCrewAI to assist in meeting preparation.

A Study assistant which helps you in doing assignment and exams

Reference agent workflow using System R AI finance tools for decision-support examples.

A CrewAI-powered multi-agent system that helps users organize travel plans by finding transportation, accommodations, activities, and providing weather-based clothing advice, destination history, and comprehensive travel reports.

This is a basic workflow with CrewAI agents working with sales transactions to draw business insights and marketing recommendations. The agents will work on everything from the execution plan to the business insights report. It works with local LLM via Ollama (I'm using llama3:8B but you can easily change it).

Chonost Manuscript OS คือระบบจัดการต้นฉบับอัจฉริยะที่ออกแบบมาเพื่อรองรับการทำงานร่วมกันระหว่าง AI agents, RAG pipelines และแอปพลิเคชันเดสก์ท็อปแบบ native โดยใช้สถาปัตยกรรม MCP (Modular Component Protocol) เพื่อให้ทุกส่วนของระบบสามารถสื่อสารกันได้อย่างเป็นอิสระและตรวจสอบได้

Generate standard operating procedures (SOPs) using CrewAi

An AI-powered financial research crew built with CrewAI. It finds trending companies, researches them, and selects the best investment candidate using hierarchical task orchestration, structured outputs, and custom tools like push notifications.

Advanced AI assistant combining RAG + Knowledge Graph with multi-agent system, persistent memory, and hybrid retrieval. Features CrewAI coordination, Neo4j integration, and dual interfaces for intelligent conversational AI.

Supercharge your AI workflows by combining Anyparser’s advanced content extraction with Crew AI. With this integration, you can effortlessly leverage Anyparser’s document processing and data extraction tools within your Crew AI applications.

A Multi Agent RAG Application built with LangGraph, CrewAI and Pathway. The App simulates the working of an Indian Legal Court.

Multi-agent AI pipeline in Python that turns a plain-text idea into a complete, scaffolded full-stack project — backend, React UI, tests, and git-ready to push. Powered by CrewAI, Anthropic Claude and Inspect AI

HuberMind - A Andrew Hyberman's Youtbe Videos Blog Generated & Download it in PDF with AI Agents, powered by Gemini, CrewAI & Towards-GenAI

A web application that creates comprehensive reports on any topic using AI agents.

An end-to-end Agentic AI application that transforms a single blog or article URL into a complete podcast episode with downloadable AI-generated voice audio.

Utilizing state-of-the-art AI-driven components, MemoGen handles the writing, outlining, and reviewing of memos. The final output is a detailed and well-structured document in DOCX format.

BotSmith is a modular multi-agent automation framework that orchestrates autonomous workflows using LLM-powered agents. It emphasizes clean architecture, dependency injection, and provider-agnostic LLM integration, enabling reliable task execution, extensibility, and transparent agent collaboration.

A Personal Voice Assistant that performs a multitude of tasks for you on command (Codeshastra X Project by Tensionflow)

Experimental AutoGen project where agents autonomously create, register, and collaborate across a distributed runtime. Each agent generates unique business ideas — showcasing self-replicating AI behavior, multi-agent coordination, and creative autonomy.

Social Media Automation System

Project GenieCart is an AI-driven e-commerce tool designed to streamline product data management and categorization. It leverages advanced machine learning models and AI agents to automate data analysis, filtering, and organization.

This repo contains the code for the AutoGen + MCP tutorial

Enables Autogen agents to securely execute code in isolated remote sandboxes using YepCode’s serverless runtime.

testing autogen

An experimental repo for pitting LLMs against each other in a game of Werewolf.

Reference example: FastAPI + Dishka DI + AG2.beta (autogen.beta) agents streaming over AG-UI SSE, wired via dishka-ag2

🔍 Analyze financial data seamlessly with the AutoGen Financial Analysis System, offering risk assessment and quantitative insights through a multi-Agent framework.

POC R&D : Une équipe d'agents IA autonomes pour construire vos logiciels. Orchestrés par un superviseur, des agents Analyste et Développeur utilisent une architecture RAG et des LLMs (Mistral) pour gérer la conception, le code, les tests et la documentation de manière 100% autonome.

AI terminal integration. Multi-purpose, cross-platform task automation & execution tool, supporting AutoGen multi-agents, for AI/LLM & other kinds of tasks. Created by David Joffe @davidjoffe. Business Source License. NOTE For some tasks this tool may modify files. Use with caution in a sandbox copy of your files 1st

A Support Chatbot demonstrating Autogen handoff pattern

MedSafeGuard combines AI efficiency with human medical expertise by automatically analyzing patient data, generating treatment recommendations, and streamlining the approval process based on risk level - only requiring physician confirmation for high-risk interventions.

RAG Framework Leaderboard — 6 frameworks, 70 adversarial tests, weekly auto-refresh. Live at wauldo.com/leaderboard

Medical Chatbot is an innovative project leveraging advanced NLP models and vector database technologies to provide insightful medical information. Utilizing the Mistral model and Pinecone as a vector database, this chatbot aims to transform the way medical knowledge is accessed and delivered.

A comprehensive guide to advanced RAG techniques including reranking, deep memory, and vector store optimization. Includes practical implementations and best practices using LlamaIndex, Langchain, etc..

Flask API with a Streamlit ChatBot, this project provides a dynamic interface for database interaction and AI-driven user engagement, featuring secure, Docker-deployed components and advanced GPT-3.5 integration.

AI Chatbot using a Streamlit interface

Streamlit powered Python Chatbot with Retrieval Augmented Generation on LLMs

In Development

Webify is an innovative tool that converts YouTube videos into fully functional websites, leveraging the power of LLaMA 3.1 for advanced content extraction and processing. Powered by cutting-edge AI technologies like LLaMA 3.1, Webify ensures a seamless experience in transforming video content into responsive website and allows you download it.

RAG-based chatbot system using open-source models and context-aware chunking strategy

Using open-source Llama2 as an alternate to OpenAI

API for MaxBot, healthcare and doctor recommendations chatbot

Chatting with PDF documents using large language models (GPT)

A RAG chatbot which enables user to chat with their pdf documents

https://youtu.be/Uh_RuwzCZhg

LLM-based Q&A on preloaded docs, raw data, Wikipedia articles and scraped web pages with knowledge graphs, analytics, charts and Streamlit interface

AI based, Document querying app that lets you upload pdf and query anything about it!

PromptPal: An AI-powered command-line assistant built using LlamaIndex & OpenAI Chat Model over custom data

Machine Learning Copilot Agent

Imagine a world where your mechanical tasks are streamlined and optimized by a knowledgeable and ever-learning assistant. That's the vision behind this LLM project: a powerful mechanical assistant trained on a vast dataset of mechanical data.

ChatTube is a project that allows users to input a YouTube link, preprocess the video, and query the content of the video using advanced AI technologies.

🍽️ AI agent powered by a ranking recommendation system and LLM to help users discover the best dining spots in Vietnamese cities like Ho Chi Minh City and Hanoi.

Interactive dataset exploration AI agent built with LlamaIndex

Generate documentation using Hugging Face embeddings and local LLMs

GoalWeaver is a compact, production-grade toolkit for agentic AI. It turns high-level objectives into a DAG of goals, schedules them adaptively, routes each goal to the right agent, and persists progress so you can visualize the run in real time.

One click starts Zero-Prompt discovery, a live Kanban ranks GO ideas, and vibeDeploy builds and deploys the selected app to DigitalOcean.

A lightweight task routing protocol for AI agents. Agents publish tasks and other agents claim them based on capability.

🕸️ Self-Optimizing Multi-Agent AI System on AWS — Routes tasks to specialized AI agents (Coder, Researcher, Summarizer) with auto-verification, self-correction, and vector-cached memory. Built with Step Functions, Bedrock, and OpenSearch Serverless.

Context engineering toolkit for LLMs — pack, cache, debug, red-team, and orchestrate context windows. Council of Experts, adversarial testing, immune system, context compiler, drift detection, multi-agent entanglement. TypeScript + Python.

Spec-driven workflow plugin for Claude Code / CodeBuddy with advisory hooks, phase selectors, locks, and task-swarm.

AI Collective Intelligence Protocol (AI-CIP): An open protocol for AI agents to voluntarily interconnect, share knowledge, and coordinate around a shared purpose.

Multi-agent AI job application system — LangGraph · FastAPI · React · MySQL · Groq Llama 3.1

Planera is an agentic analytics copilot that turns natural language questions into structured, explainable analysis over uploaded data.

LaunchIQ: AI-powered product launch intelligence with a multi-agent pipeline (market intel, personas, strategy, content).

Multi-agent research pipeline for Claude Code — web crawl, knowledge graph, synthesis, and citation-rich reports via slash commands.

Multi-agent system for grading discursive exams, with RAG support and conditional divergence arbitration. Capstone project (TCC) at Instituto Federal Fluminense. Built with LangGraph, LangChain, FastAPI, ChromaDB, and PostgreSQL.

Opinionated Claude Code setup for managing 10+ apps with multi-agent orchestration

Multi-agent reinforcement learning (MARL) for relaxed probability updating games. This repository corresponds to the master thesis project "Investigating relaxed probability updating games" by Collin Aldaibis