Ask HN: How do you manage your AI agents' context across clients and projects?
Summary
Ask HN about how people manage AI agents' context across clients and projects. The thread gathers multiple real-world approaches to preserving and isolating context, including using exemplar contexts from prior projects, per-client memory isolation, and lightweight memory architectures; several contributors share tools and patterns like issue trackers, ADRs, the Johnny Decimal system, and self-hosted LLM setups to prevent context leakage and streamline resumption of work across clients.