In this paper, we describe LLMoxie, an institutional AI platform whose three-tiered architecture supports multi-cloud and on-premise inference. The platform includes a LiteLLM/MLflow control plane for authentication, budgeting, PII masking, and observability, along with an application augmentation layer for AI coding agents. On top of this, an open-source RSE-Plugins ecosystem encodes accumulated RSE knowledge as a Plugin-Agent-Skill hierarchy, spanning scientific Python practice, domain-specific knowledge, a six-phase research-and-implement workflow, and project lifecycle management.
Scientific software is judged less by raw code quality than by whether it can be cited, audited, reproduced, and extended. Off-the-shelf AI coding agents, optimized against commercial software benchmarks, are poorly calibrated for this setting: they ignore the conventions of the scientific Python libraries they invoke, mishandle sensitive or embargoed data, and leave decision trails that are difficult to reconstruct after the fact.
We report on twenty months of practice at a university-based research software engineering (RSE) center, where RSEs embedded across astronomy, earth and climate science, agriculture, and health projects worked to close this gap. We characterize the recurring infrastructure, governance, and process challenges of adopting Agentic AI inside a multi-domain RSE center, describe the platform and plugin design, and distill operational lessons from real scientific software deployments. Together, the platform and plugins shift AI coding agents from generic code generators into domain-aware collaborators that respect community norms and produce auditable provenance of technical reasoning.
Blogger's Review: LLMoxie's three-tiered architecture not only showcases AI's potential in scientific software development but also emphasizes the importance of adhering to community norms in multi-domain collaborations. The plugin ecosystem empowers AI coding agents to better adapt to the complex demands of scientific research, enhancing both the quality and transparency of research software.