AutoGen

Top Builders

Explore the top contributors showcasing the highest number of app submissions within our community.

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

Edit on GitHub

AutoGen AI technology page Hackathon projects

Discover innovative solutions crafted with AutoGen AI technology page, developed by our community members during our engaging hackathons.

Wisdom AI : Reviving Ancient Wisdom Through AI

WisdomAI: Reviving Ancient Wisdom with AI WisdomAI is a multilingual, source-grounded AI platform that makes centuries-old wisdom accessible to today’s generation in any language. Many young people have deep questions about life, ethics, purpose, non-violence, relationships, stress, self-discipline, and decision-making, but ancient wisdom is often locked inside old books, difficult languages, scanned manuscripts, or limited access to scholars. WisdomAI solves this by allowing users to upload wisdom texts, create a private knowledge index, and ask questions in natural language. Users can ask in one language and choose the answer language, such as English, Hindi, Gujarati, Sanskrit, Sinhala, or other global languages. The system then provides detailed answers grounded only in the selected uploaded book, with source references for transparency. Unlike generic AI chatbots, WisdomAI does not answer from broad model knowledge. It uses a document-specific RAG pipeline where each uploaded book is isolated, indexed, and searched independently. When a user asks a question, WisdomAI retrieves only the most relevant passages from the selected book and asks Gemini to generate an answer strictly from that evidence. If the selected book does not contain enough information, WisdomAI refuses gracefully instead of hallucinating. A key innovation is Quarantine Mode for Poisoned Books. Before any uploaded text enters the RAG pipeline, WisdomAI scans it for hidden prompt injection, malicious instructions, or attempts to override system behavior. If unsafe content is detected, the document is quarantined, the triggered safety rule is shown to the user, and the poisoned book is blocked from indexing and retrieval. This protects the integrity of the knowledge base and makes the system safer for educational, cultural, and research use.

Agent Surface

AgentSurface is a tool for testing the security of real AI agents that are exposed through HTTP JSON APIs. Instead of relying on mock agents or generic jailbreak examples, AgentSurface connects to an actual agent endpoint, injects adversarial prompts into a configurable JSON request field, sends real HTTP requests, and records the full evidence trail: masked request, raw response, extracted answer, finding type, risk score, and recommendations. The project focuses on practical risks in AI-powered products: prompt injection, system prompt or secret disclosure, private data exposure, unsafe tool/action compliance, BOLA/IDOR-style cross-user access, and authorization gaps in support, finance, trading, CRM, and marketplace agents. AgentSurface includes a Streamlit UI with three main workspaces: Attack Sets for creating reusable adversarial prompt sets, Run for configuring the real API target and launching scans, and History for reviewing previous runs, findings, raw evidence, JSON exports, and policy drafts. It can also generate a Lobster Trap YAML policy draft, helping teams turn some detected risks into proxy-layer mitigations when applicable. The main idea behind AgentSurface is to treat an AI agent as an attack surface, not just as a chatbot. It helps teams test whether their agent follows security and business rules under adversarial input, while keeping concrete evidence that developers can use to debug and fix the issue.

Zynaptrix Context-Aware RAG (Gemini AI)

Zynaptrix is a context-aware RAG system built around Google Gemini and a modular agent pipeline to convert heterogeneous documents into accurate, professional reports. The backend ingests PDFs and images, uses a captioner, figure-splitter, and table transformer to extract structured content, then creates embeddings and indexes for fast retrieval. An orchestrator agent composes retrieved context with Gemini-powered synthesis; a report-writer agent formats outputs into exportable documents while a safety-critic agent enforces guardrails. The architecture separates ingestion, embedding, retrieval, and generation concerns so teams can add new extractors or retrievers easily. The frontend provides an assistant API and machine-focused workflows for interactive querying and batch report generation. Designed for research and enterprise use, Zynaptrix emphasizes provenance (source links and extracted snippets), multimodal understanding (text, figures, tables), and reproducible report generation for knowledge workers, analysts, and technical communicators

ChaosMonkey MCP

ChaosMonkey MCP is a local-first MCP server for autonomous fault injection and crash discovery. It gives AI agents such as IBM Bob, Claude, Cursor, and Codex provider-agnostic chaos engineering tools that can stress-test local projects, inject failures, execute commands, and identify resilience issues automatically. The project focuses on autonomous crash discovery rather than remediation. ChaosMonkey MCP does not modify repositories or generate fixes. Instead, it helps AI agents uncover hidden failure modes such as null-handling bugs, malformed payload assumptions, weak validation, and fragile error handling. The platform currently includes: * fault injection through nested null mutation, * repeated chaos execution with deterministic seeds, * structured crash and traceback reporting, * safe local command execution, * secure local file reading, * a production-ready local FastMCP server. ChaosMonkey MCP runs entirely locally over stdio using the Model Context Protocol, without requiring any cloud backend or hosted infrastructure. The project was developed using IBM Bob IDE during the hackathon, including the MCP architecture, tool design, fault injection workflows, and crash discovery pipeline. It demonstrates how IBM Bob can be used to design AI-native developer tooling and autonomous resilience testing workflows.

RepoPilot

RepoPilot is an AI-powered developer onboarding platform that helps developers quickly understand complex codebases. Modern repositories are often large and difficult to navigate, making onboarding slow and confusing. RepoPilot solves this by turning repositories into an interactive, AI-driven learning experience. It connects directly to GitHub and performs deep analysis of project structure, architecture, dependencies, modules, APIs, workflows, and runtime behavior. Instead of manually exploring code, developers get structured insights and AI-generated explanations. A key feature is its Codebase Q&A Assistant, where users can ask questions in natural language and receive context-aware answers based on the repository. It also provides automatic code explanations that simplify complex modules while still supporting advanced detail. RepoPilot includes project structure visualization and dependency mapping, helping developers understand how files, services, and modules connect and how data flows through the system. It also offers runtime flow tracing to visualize execution paths step by step. A Smart Onboarding Flow generates guided learning paths based on repository complexity, ensuring developers explore important components in the right order. The platform supports Beginner and Professional modes to adjust explanation depth. Built with Next.js, React, TypeScript, Tailwind CSS, and GitHub APIs, RepoPilot reduces onboarding time and improves developer productivity by making complex systems easier to understand.