AutoGen
An Open-Source Programming Framework for Agentic AI
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for AutoGen, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
AutoGen is an open-source framework developed by Microsoft Research for building next-generation Large Language Model (LLM) applications. It enables multi-agent conversations, allowing developers to create complex AI workflows with multiple specialized agents collaborating to solve tasks. AutoGen simplifies the development of LLM-powered applications and supports various LLM configurations, tool usage, and human-AI interaction.
Key features and capabilities
- Multi-agent collaboration, Flexible LLM integration, Automated task orchestration, Code generation and execution, Human-in-the-loop capability
Use cases
- Building AI assistants, Automating software development tasks, Creating interactive learning environments, Developing complex decision-making systems, Enhancing customer service applications