text2future/flowix

Notes for you, Memory for your agents. / 内置 Deepseek harness Agent / 适用 办公 & 写作 & Coding

What it solves

Flowix provides a way to turn personal Markdown notes into a durable, shared memory for AI agents. It solves the problem of agents starting from scratch every time a project evolves, by allowing users to maintain a living document of requirements, research, and decisions that agents can read and update.

How it works

Flowix is a Markdown-based notebook application that stores files locally as plain text. It provides a CLI and an MCP (Model Context Protocol) server, allowing external AI agents (such as Claude Code, Codex, or OpenCode) to search, read, create, and edit the notes. Users can control exactly which notes or folders are shared as context for a specific agent task.

Who it’s for

  • Software Developers who want to give coding agents persistent context about their project.
  • Researchers who want to keep sources and analysis together and reusable for AI assistance.
  • Product Managers who want to keep PRDs and feedback up to date using agents.
  • Knowledge Workers who want to turn personal notes and preferences into agent context.

Highlights

  • Local-first storage: Notes are saved as plain Markdown files on the user's device for full control and portability.
  • MCP & CLI Integration: Connects to a wide variety of external agents via a bundled MCP server.
  • Bidirectional updates: Agents can not only read context but also save results back into the notes for future use.
  • Granular context control: Users choose specifically which notes, folders, or notebooks are shared with agents.

Related

  • Project
    akitaonrails/ai-memory

    ai‑memory is a Rust‑based, self‑contained service that gives AI coding assistants a shared, long‑term, markdown‑backed memory. It automatically captures prompts and tool calls via hooks, stores them as git‑versioned markdown pages, and lets any supported agent (Claude Code, Codex, Cursor, Gemini CLI, etc.) retrieve a concise hand‑off on a different machine or after a teammate’s session. By default it works offline with zero LLM calls; optional LLM‑driven “dream” consolidation, vector search, and aging policies are configurable. The project provides native packages, Docker images, and a macOS menu‑bar app, and includes built‑in multi‑user auth, audit logs, and per‑project sharing.

  • Project
    iwe-org/iwe

    IWE is an open‑source suite that stores project notes in plain‑text Markdown files and lets LLM agents (Claude, Codex, Gemini, etc.) read, write and organise those notes. It provides a native macOS app, editor plugins, a terminal CLI, and a Model‑Context‑Protocol server so humans and agents share the same editable knowledge base.

  • Project
    mcncarl/agent-memory-vault

    A Python‑based, local‑first system that lets Claude Code, Codex and similar agents store and retrieve shared knowledge in a private Markdown vault. The vault is versioned with Git, indexed with SQLite (and optionally a local embedding vector store), and all writes go through a strict read‑prepare‑authorize‑apply workflow that records immutable receipts. It provides searchable, auditable long‑term memory for AI coding assistants while keeping the data private to the user.

  • Project
    OthmanAdi/planning-with-files

    A persistent file-based planning system for AI coding agents that stores task plans, findings, and progress on disk to prevent state loss during context resets.

  • Project
    hooosberg/WitNote

    WitNote is a cross‑platform, open‑source Markdown editor that stores notes locally and offers optional AI assistance via Ollama or cloud APIs. It features instant file opening, dual‑pane live preview with LaTeX and code highlighting, strong security, and native builds for macOS (Swift/SwiftUI) and binary packages for Windows and Linux. Licensed MIT, it never uploads user data.