iwe
IWE is a markdown-based knowledge graph system that lets you organize notes as an interconnected structure rather than folders, with IDE features in your editor and CLI/MCP tools for AI agents to query and refactor your notes. Built in Rust and stored as plain markdown files you version with git, it bridges personal knowledge management with agentic AI workflows.
Key facts
Objective fields from the source. Values we can't verify are shown as “Unknown” rather than guessed.
| Field | Value |
|---|---|
| Repository | iwe-org/iwe |
| Owner | iwe-org |
| Primary language | Rust |
| License | Apache-2.0 — OSI-approved |
| Stars | 1.3k |
| Forks | 62 |
| Open issues | 1 |
| Latest release | iwe-v0.8.0 (2026-07-07) |
| Last updated | 2026-07-07 |
| Source | https://github.com/iwe-org/iwe |
What iwe is
IWE processes markdown directories into a queryable knowledge graph via LSP (VS Code, Neovim, Zed, Helix), a CLI tool suite, and an MCP server. It supports inclusion links (hierarchical nesting), cross-references, multi-parent nodes, and context propagation; the Rust backend indexes and retrieves 20,000 files in under a second. No database or cloud required; all state remains local and git-compatible.
Get the iwe source
Clone the repository and explore it locally.
git clone https://github.com/iwe-org/iwe.gitcd iwe# follow the project's README for install & configurationNeed it deployed, integrated, or customized instead? DEV.co ships production installs.
Best use cases
Implementation considerations
- Rust toolchain required to build from source via Cargo, or use Homebrew on macOS/Linux. Binaries for other platforms not mentioned in data.
- Project is young (created Sept 2024, now at v0.8.0 as of July 2026); breaking changes in the markdown format or link syntax are possible before 1.0.
- LSP and MCP server setup requires editor-specific configuration and may need documentation review for less common editor setups.
- CLI is the integration point for scripts and AI workflows; ensure your AI tool or shell environment can invoke and parse iwe commands reliably.
- Graph scale and performance at 20k+ files not tested in your own environment; measure indexing and query time for your specific note volume and link density.
When to avoid it — and what to weigh
- You need cloud sync or multi-device real-time collaboration — IWE is file-based and local. Syncing across devices requires external tooling (git, Syncthing, etc.); there is no built-in cloud backbone or conflict resolution for simultaneous edits.
- You require ACID transactions or guaranteed data consistency — IWE reads and writes markdown files on disk with no transactional guarantees. High-concurrency scenarios (many processes touching the same graph simultaneously) are not addressed in the data provided.
- Your team uses proprietary knowledge systems or closed formats — IWE ties you to markdown and its link syntax. Migration to or from proprietary formats is not documented and may require manual effort.
- You need off-the-shelf AI models built in — IWE has no embedded LLM. It is a **context provider** for external AI tools (Claude, Gemini, etc.); you must manage your own AI integrations and API keys.
License & commercial use
Apache License 2.0 is a permissive, OSI-approved open-source license. It grants rights to use, modify, and distribute the software, including for commercial purposes, provided you include a copy of the license and document material changes. Liability is disclaimed.
Apache 2.0 explicitly permits commercial use. However, no support SLA, warranty, or indemnification is included in the license. Enterprises should review the warranty disclaimer and consider commercial support arrangements (not mentioned in the repo data) independently.
DEV.co evaluation signals
Editorial assessment — not user reviews. Directional, with an explicit confidence level.
| Signal | Assessment |
|---|---|
| Maintenance | Active |
| Documentation | Strong |
| License clarity | Clear |
| Deployment complexity | Low |
| DEV.co fit | Good |
| Assessment confidence | High |
IWE reads and writes markdown files locally; no authentication or encryption is built in. Security model relies on OS file permissions. The MCP server exposes file operations via a network interface—ensure it is only bound to localhost or trusted clients. No data is sent to external servers by default. Markdown injection (e.g., via links) in untrusted note sources could affect editor behavior; validate note inputs if pulling from external sources. No third-party dependency security audit is provided here.
Alternatives to consider
Obsidian
Commercial, Electron-based note app with built-in graph visualization, sync, and community plugins. Proprietary format and cloud tie-in may reduce portability compared to IWE's plain markdown.
Logseq
Open-source outliner with knowledge graph features and Electron UI. Stores in EDN or markdown; less CLI-native and MCP integration not standard, but mature community and plugin ecosystem.
Dendron
VS Code extension for hierarchical note management with backlinking. Focused on editor experience; lacks standalone CLI and MCP server for agentic workflows compared to IWE.
Build on iwe with DEV.co software developers
Evaluate IWE for your team's research, documentation, or personal knowledge workflows. Start with the quick install, set up your editor, and test integration with your AI tools via MCP or CLI.
Talk to DEV.coRelated open-source tools
Surfaced by semantic similarity across the DEV.co open-source index.
Related on DEV.co
Explore the category and the services that help you build with it.
iwe FAQ
Can I use IWE on multiple devices?
Does IWE include an AI model?
What if I want to switch away from IWE later?
Is IWE ready for production use?
Custom software development services
DEV.co is a software development agency delivering custom software development services to companies building on open source. Our software developers and web developers design, integrate, and ship production systems — spanning web development, APIs, AI, data, and cloud. If iwe is part of your mcp servers roadmap, our team can implement, customize, migrate, and maintain it.
Ready to organize your knowledge for AI?
Evaluate IWE for your team's research, documentation, or personal knowledge workflows. Start with the quick install, set up your editor, and test integration with your AI tools via MCP or CLI.