bounded-agent is a Python library offering five small primitives that implement contract-bounded autonomy for LLM agents. It makes agents safe to run autonomously by enforcing behavioral contracts and safety boundaries. Designed for developers building reliable AI agent systems that can be left to operate independently without risk of unintended actions.
bounded-agent is an AI & ML project. It focuses on preventing unsafe or unbounded behavior when running autonomous LLM agents. bounded-agent is an open-source project aimed at developers. The project is open source (MIT). bounded-agent is available on the command line and API.
bounded-agent first shipped in 2026. The project is developed in the open on GitHub with 4 commits in the last 90 days. Key capabilities include contract bounding, agent safety primitives, and autonomy controls.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do