lastmile-ai/mcp-agent
dottxt-ai/outlines
getomni-ai/zeroxAn AI agent wraps a large language model in a loop: it reasons about a goal, chooses an action (often calling an external tool or API), observes the result, and repeats until the task is done. The defining trait versus a plain chatbot is autonomy — the model decides the next step rather than just answering one prompt.
Open-source agent frameworks provide the scaffolding for this loop: tool/function calling, memory, planning, and multi-agent orchestration. They range from coding agents that edit and run your repository to general task agents that browse the web or operate software.
