AutoGen

AutoGen is an advanced open-source framework developed by Chi Wang designed to simplify the creation of multi-agent systems powered by large language models (LLMs). The platform allows developers to build conversational AI agents that can interact with each other, humans, and various tools in a coordinated manner. AutoGen is highly modular and supports a wide range of applications, making it an essential tool for developers looking to implement complex, automated workflows with minimal manual intervention.

General
Author	Chi Wang
Release Date	September 2023
Website	https://microsoft.github.io/autogen/
Repository	https://github.com/microsoft/autogen
Documentation	https://microsoft.github.io/autogen/docs/Getting-Started
Discord	https://discord.com/invite/pAbnFJrkgZ
Technology Type	AI/ML Framework

Key Features

Multi-Agent Framework: Facilitates the design of agents with specialized roles, enabling them to communicate and collaborate efficiently.
Enhanced LLM Inference: Provides advanced APIs for improving LLM performance, reducing inference costs.
Customizable Workflows: Supports complex, dynamic workflows by allowing agents to interact through conversational patterns, enabling seamless automation.
Tool Integration: Agents can be configured to use external tools, adding flexibility and enhancing their problem-solving capabilities.
Human-in-the-Loop: Integrates human feedback into the workflow, allowing for oversight and intervention when necessary.

Start Building with AutoGen

AutoGen simplifies the development of complex AI applications by providing a robust framework for creating multi-agent systems. With its modular design, developers can quickly build and customize AI workflows that combine LLMs, human intelligence, and various tools to tackle intricate tasks. Whether you are looking to automate customer support, enhance software development processes, or optimize supply chains, AutoGen offers the flexibility and power needed to create sophisticated AI-driven solutions. Explore the community-built use cases and applications to see the full potential of what AutoGen can do.

👉 Start building with AutoGen

👉 Examples

ProveRun

ProveRun is a Blast Radius Zero (Pattern A) web agent for Vultr Agent Rush. A user asks a question in the browser (optionally with a CSV); Vultr Serverless Inference writes Python; the code runs in a disposable Docker sandbox with no network, memory and time caps, dropped capabilities, and a read-only root. Real stdout returns to the model for a short explanation. Secrets stay in the API process and never enter the sandbox. The control plane runs on a Vultr Cloud Compute VM. Live demo: http://140.82.0.23:8787 — Public GitHub: https://github.com/happy-star/proverun — Judges can use the in-app containment test: network probes, secret reads, and host writes fail while the host canary stays unchanged.

NURDA6FOOT4

SDSADASDDASDSADASD ka dwkec keCJWeofweokMsdcosmks slnl;seNCVL;wenvipuwernfuiwnwoerf SDSADASDDASDSADASD ka dwkec keCJWeofweokMsdcosmks slnl;seNCVL;wenvipuwernfuiwnwoerf SDSADASDDASDSADASD ka dwkec keCJWeofweokMsdcosmks slnl;seNCVL;wenvipuwernfuiwnwoerf SDSADASDDASDSADASD ka dwkec keCJWeofweokMsdcosmks slnl;seNCVL;wenvipuwernfuiwnwoerf SDSADASDDASDSADASD ka dwkec keCJWeofweokMsdcosmks slnl;seNCVL;wenvipuwernfuiwnwoerf SDSADASDDASDSADASD ka dwkec keCJWeofweokMsdcosmks slnl;seNCVL;wenvipuwernfuiwnwoerf SDSADASDDASDSADASD ka dwkec keCJWeofweokMsdcosmks slnl;seNCVL;wenvipuwernfuiwnwoerf SDSADASDDASDSADASD ka dwkec keCJWeofweokMsdcosmks slnl;seNCVL;wenvipuwernfuiwnwoerf SDSADASDDASDSADASD ka dwkec keCJWeofweokMsdcosmks slnl;seNCVL;wenvipuwernfuiwnwoerf SDSADASDDASDSADASD ka dwkec keCJWeofweokMsdcosmks slnl;seNCVL;wenvipuwernfuiwnwoerf SDSADASDDASDSADASD ka dwkec keCJWeofweokMsdcosmks slnl;seNCVL;wenvipuwernfuiwnwoerf

AdvancedLeads AI — Multi-Agent Lead Scoring

B2B lead qualification is usually a single model's judgment call, and single-model judgment is unreliable: it's confident, opaque, and hard to audit. AdvancedLeadsGeneration-AI replaces that with a structured debate between agents, then a scored reconciliation against historical deal data. The system runs three roles. An advocate agent argues why a lead is a strong fit, citing signals from the lead's profile and company data. A risk agent argues the opposite — surfacing counter-evidence, red flags, and gaps in the data. A reconciliation layer then scores both arguments against historical won/lost deal patterns and produces a final lead score with the reasoning attached, so a sales team can see not just the score but why it was given. The key design decision was separating advocacy from risk assessment. A single prompt asking a model to "evaluate this lead" tends to collapse into one perspective. Forcing two agents to argue opposing positions, then having a third layer judge between them, produces more balanced output and surfaces concerns a single-pass evaluation would miss. We built it on IBM Granite models via IBM Watsonx.ai, with a FastAPI backend exposing the workflow as public-facing REST APIs and a Next.js frontend. The project won the IBM Granite Hackathon on lablab.ai (Team PolyEns, February 2025). The architecture and API contracts are documented publicly in the repository so the debate-and-reconcile pattern can be reused for other scoring workflows — vendor evaluation, candidate screening, or any decision where a single model's opinion isn't enough.

Factory Agent: AI Quality & Maintenance Assistant

Factory Agent is an end-to-end AI quality inspection and industrial maintenance assistant designed for modern manufacturing environments. It addresses costly equipment downtime and the safety risks of unverified AI recommendations through multimodal defect detection, retrieval-augmented generation (RAG), evidence-grounded diagnosis, and human-in-the-loop governance. The system accepts machine-part photographs, sensor telemetry reports in CSV, JSON, or TXT formats, and technical inspection documents in TXT or PDF formats, including OCR-based text extraction. For visual inspection, Factory Agent combines an advisory local CNN with AMD Token Factory vision models, including Qwen3.8-Flash-Next and Gemma-4-31B-IT. It evaluates individual model predictions rather than averaging confidence scores, flagging low-confidence results and disagreements as UNVERIFIED for expert review. Its RAG pipeline retrieves relevant maintenance procedures from technical manuals. Primary and fallback language models, MiMo-V2.6-Flash and DeepSeek-V4-Flash, generate diagnostic explanations and repair recommendations grounded in retrieved evidence. The system validates recommendations against source manual text and provides citations identifying relevant manuals and pages where available. A human-in-the-loop interface enables plant managers to review predictions, examine supporting evidence, and approve or reject proposed maintenance actions. Only approved cases proceed to Evolus automation workflows for maintenance work-order generation. Built with Next.js, React, TypeScript, FastAPI, PyTorch, and Docker, Factory Agent supports cloud integrations and an offline mock mode for demonstrations and development without API keys. By combining automation, traceable evidence, and human oversight, Factory Agent aims to make industrial AI safer, more transparent, auditable, and practical.

CyberLens - AI Cybersecurity Intelligence

CyberLens — Digital Safety & Cybersecurity Intelligence is a web-based platform designed to help users identify potential online threats before they become serious security risks. The platform analyzes URLs, QR codes, and screenshots to detect suspicious patterns and highlight possible cybersecurity risks. It combines URL risk analysis, QR code scanning, screenshot text extraction using OCR, and explainable risk scoring to help users understand why a link or piece of digital content may be suspicious. Instead of presenting only a risk score, CyberLens provides understandable signals and warnings that help users make more informed decisions. Its goal is to make cybersecurity awareness more accessible to students, everyday internet users, and people who may not have technical security knowledge. Built using Next.js, TypeScript, Tailwind CSS, Tesseract.js, and jsQR, CyberLens brings multiple digital safety checks into a unified interface. The project focuses on practical security awareness, transparent analysis, and a user-friendly experience. CyberLens does not claim that every suspicious indicator proves malicious activity. It provides risk assessments and supporting signals to help users investigate potential threats more carefully. **Tagline:** See the hidden risk before it becomes a threat.

HandSpeak

SignBridge is a real-time AI-powered sign language interpretation system designed to make communication more accessible between sign language users and people who do not understand sign language. Using a camera, the system detects hand and body movements, analyzes gesture sequences, and converts recognized signs into natural-language text and speech. The project will leverage AMD GPU acceleration to improve real-time computer vision and AI inference performance, allowing the system to process video with low latency. Beyond individual signs, SignBridge aims to recognize sequences of gestures and reconstruct meaningful phrases, making communication more natural. The project combines accessibility, computer vision, AI, and high-performance AMD computing to create a practical assistive technology solution.