mayneyao/eidos

A single-file relational spreadsheet for you and your agent.

What it solves

Eidos provides a structured, local-first data format and environment designed to be readable and manipulatable by both humans and AI agents. It bridges the gap between unstructured Markdown notes and structured relational databases, ensuring your data remains portable, offline-accessible, and programmatically accessible.

How it works

At its core, Eidos uses a single-file format built on SQLite. It provides a cross-platform ecosystem including a desktop app (Eidos Lite), mobile apps (Android/iOS), and a CLI. The CLI allows users to programmatically create, query, and update these files, making it suitable for agentic workflows where an AI needs to read or modify structured personal data. The system uses a shared runtime and UI components across web, desktop, and mobile platforms.

Who it’s for

It is for power users, developers, and AI enthusiasts who want a local-first knowledge management system that allows AI agents to interact with their personal data through a structured, relational interface.

Highlights

  • Single-file relational format based on standard SQLite.
  • Agent-first CLI for querying and updating data via automation.
  • Cross-platform support including desktop, mobile, and browser-based editors.
  • Local-first architecture that functions offline without requiring an account.
  • Built-in support for Eidos-flavored Markdown alongside relational tables.

Related

  • Project
    tursodatabase/agentfs

    AgentFS is a SQLite-based filesystem designed for AI agents that provides persistent storage, key-value state management, and a full audit trail of tool calls in a single portable file.

  • Project
    openagents-org/openagents

    An open-source collaborative OS for AI agents that provides a unified workspace where multiple agents can share threads, files, and a browser to work together.

  • Project
    Ephemeral-AI-Lab/layerfs

    LayerFS is a Rust‑based, SQLite‑backed storage engine that gives AI agents cheap, immutable snapshots of their filesystem workspaces. Using content‑addressed storage, content‑defined chunking, and copy‑on‑write, it deduplicates data across many parallel agent runs. A CLI and FUSE container runtime let you create a Store, start a workspace, commit changes as immutable layers, and fork new branches without copying files. The v0.1.6 preview demonstrates strong storage efficiency but lacks durability guarantees and cross‑host sync. It’s a research‑grade foundation for building agents that need fast, versioned filesystem state.

  • Project
    busabase/busabase

    Busabase is an open‑source, local‑first database + workspace that lets AI agents (Claude Code, Codex, Cursor, Gemini, etc.) and people share structured records, docs, skills, and tiny apps. Every agent write is stored as a Change Request with diff, author, and history, enabling durable, auditable multi‑agent workflows. It runs via a simple `npx busabase server` command (or Docker/desktop), supports templates, and offers an API (MCP/OpenAPI) for any custom agent.

  • Project
    citrolabs/ego-lite

    ego lite is a specialized browser designed for AI agents to perform web automation tasks in isolated, parallel workspaces without interrupting your personal browsing.