OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Memory & RAG

Iwe

Iwe is a Markdown knowledge graph for keeping project notes, such as plans, specifications and decisions, in a shared folder that people and AI agents can access. It provides a language server for editor workflows, a CLI, an MCP interface and a native Mac app.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Iwe — OpenViST project profile in Agent Memory & RAG.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Iwe when project context should live in Markdown files that both you and your AI tools can inspect and maintain across work sessions.

Who it is for

  • People who want project notes to remain readable and editable outside an AI agent.
  • Developers who want Markdown note navigation and backlinks in a supported editor.
  • AI-agent users who want to connect shared project notes as persistent context.

Documented uses

  • Save and retrieve project decisions across AI conversations.
  • Create, search and reorganize Markdown knowledge-base content from the terminal.
  • Navigate linked notes and use backlinks and autocomplete in an editor.
  • Let a compatible agent read, write and organize shared notes through MCP.
Before you choose

Requirements & limits

The CLI and notes work without an Iwe cloud account. The CLI and Mac app do not include an AI model; connecting an agent uses that agent’s own setup and account requirements.

  • Notes are Markdown files in a local folder, which can be backed up, synced or kept in git.
  • The editor language server, CLI, Mac app and agent connection operate on the same documents.
  • The project is open source under the Apache-2.0 license.
  • Connecting an MCP-compatible agent is a documented adaptation: it can access shared Markdown notes as memory. Specific agent-client setup requirements vary and are not detailed here.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install IWE and initialize a Markdown workspace

Install IWE, initialize a workspace in an existing notes directory, and begin using its Markdown knowledge-graph features.

Before you start

  • An existing notes directory.
  • For Cargo installation, Rust and Cargo.

Steps

  1. Install IWE using a documented option: run the command below and the command below if Rust is available, or use another installation method listed in the Quick Start.

    Documented command
    cargo install iwe
    Documented command
    cargo install iwes

  2. Navigate to your notes directory and run iwe init. This creates .iwe/config.toml with default configuration.

  3. Write Markdown files in the workspace and use the documented features, including global note search, link autocomplete, and navigation through links.

Expected outcome

An initialized IWE workspace with Markdown notes and documented knowledge-graph features available.

Guide limitations

  • IWE has no built-in AI; it is designed to work with external AI tools.
  • The documentation does not specify an agent-connection workflow in this setup sequence.
Documentation 1 ↗Documentation 2 ↗
Evidence and transparency

Sources & review

Official repository ↗Guide documentation ↗Guide documentation ↗
Source record details
Source availability
Active
Sources checked
10 October 2026
Original website title
iwe-org/iwe · Official homepage title · retained in its source language
How we review sourcesSuggest a correction