agent0ai/dox

Self-documenting AGENTS.md

What it solves

AI agents often edit code blindly or lose track of project-wide rules, leading to "drift" and unexpected changes. DOX provides a structured way for agents to maintain and follow precise project context across a codebase.

How it works

DOX is a lightweight framework based on a hierarchy of AGENTS.md files. The agent starts at a root AGENTS.md for project-wide instructions and traverses down to child AGENTS.md files for local guidelines specific to certain areas of the project. Before making any edit, the agent reads this documentation tree to understand the local rules; after making changes, it updates the documentation to keep it current.

Who it’s for

Developers using AI agents (such as Codex, Claude Code, or OpenCode) to manage and edit their software projects.

Highlights

  • Zero installation: No dependencies, packages, or runtimes required.
  • Hierarchical context: Uses a tree of Markdown files to provide local and global instructions.
  • Self-maintaining: The agent updates the documentation as the project evolves.
  • Agent-agnostic: Works with any AI agent that supports reading Markdown files.

Related

  • Project
    mex-memory/mex

    A shared project memory system for engineers and AI agents that stores architectural decisions and context as version-controlled Markdown in Git, linked to a local code graph.

  • Project
    agentsmd/agents.md

    An open format for creating AGENTS.md files to provide AI coding agents with project-specific context and instructions.

  • Project
    agent0ai/agent-zero

    Agent Zero is an open‑source Docker‑based framework that gives an LLM‑driven AI agent a full Linux desktop, a browser with DOM‑annotation, live document editors, and a plugin ecosystem. Agents can run GUI apps (e.g., Blender, LibreOffice), edit files, browse and annotate web pages, and even spawn sub‑agents, all while you watch and intervene through a web UI. Installation is via a cross‑platform launcher or a one‑line script, and the system supports project‑scoped workspaces, host‑machine bridging, time‑travel snapshots, and extensive community plugins.

  • Project
    TokenRollAI/llmdoc

    A persistent engineering context system that helps coding agents understand a repository's architecture and design decisions without rediscovering them every session.

  • Project
    scaleapi/scale-agentex

    A framework for building and deploying AI agents that scales from simple chatbots to fully autonomous systems, supporting both synchronous and asynchronous workflows.