Everything is Context: Agentic File System Abstraction for Context Engineering

TL;DR

The paper tackles fragmentation in context engineering for GenAI by proposing a Unix-inspired file-system abstraction that unifies heterogeneous context sources into a persistent, governed repository. It defines a Context Engineering Pipeline—comprising a Context Constructor, Updater, and Evaluator—tightly integrated with a persistent history/memory/scratchpad lifecycle and constrained by token-window, statelessness, and non-determinism. Implemented in the open-source AIGNE framework, the approach is demonstrated with two exemplars: memory-enabled context construction and an MCP-based GitHub assistant, illustrating verifiable, auditable, and human-centered AI co-work. The work lays a foundation for accountable, maintainable, and industry-ready GenAI systems by treating context as a portable, evolvable file-system resource with explicit governance and provenance.

Abstract

Generative AI (GenAI) has reshaped software system design by introducing foundation models as pre-trained subsystems that redefine architectures and operations. The emerging challenge is no longer model fine-tuning but context engineering-how systems capture, structure, and govern external knowledge, memory, tools, and human input to enable trustworthy reasoning. Existing practices such as prompt engineering, retrieval-augmented generation (RAG), and tool integration remain fragmented, producing transient artefacts that limit traceability and accountability. This paper proposes a file-system abstraction for context engineering, inspired by the Unix notion that 'everything is a file'. The abstraction offers a persistent, governed infrastructure for managing heterogeneous context artefacts through uniform mounting, metadata, and access control. Implemented within the open-source AIGNE framework, the architecture realises a verifiable context-engineering pipeline, comprising the Context Constructor, Loader, and Evaluator, that assembles, delivers, and validates context under token constraints. As GenAI becomes an active collaborator in decision support, humans play a central role as curators, verifiers, and co-reasoners. The proposed architecture establishes a reusable foundation for accountable and human-centred AI co-work, demonstrated through two exemplars: an agent with memory and an MCP-based GitHub assistant. The implementation within the AIGNE framework demonstrates how the architecture can be operationalised in developer and industrial settings, supporting verifiable, maintainable, and industry-ready GenAI systems.

Figures (3)

• Figure 1: File system as a unifying abstraction for context engineering.
• Figure 2: Lifecycle of History, Memory and Scratchpad
• Figure 3: The Context Engineering Pipeline.