SumizAI vs Minne

What Minne is

What Minne is

Minne is a Swedish personal knowledge management app whose name means 'memory' in Swedish — a fitting description of its purpose: capturing, organizing, and rediscovering information that would otherwise easily get lost among bookmarks, notes, and passing thoughts. Inspired by the Zettelkasten method, a system of note cards linked to one another, Minne uses a graph database to automatically build connections between saved items, rather than forcing the user to manually file everything into a rigid folder hierarchy.

Key features

A save-for-later feature lets you quickly set aside an article, link, or text fragment found online to return to at a calmer moment, without losing the context in which it was found. Because Minne is an open-source project under the AGPL-3.0 licence, the source code is fully open for review, and that particular licence's terms require sharing modifications even when the app is offered as a network service.

Who it's for

Minne reaches people practicing the Zettelkasten method or interested in building a personal knowledge base based on connections between ideas rather than rigid folders. It's a tool for researchers, writers, and students gathering material for longer projects who want the system itself to help surface non-obvious relationships between saved fragments of knowledge.

Use cases

Someone writing an academic paper can save fragments of articles they've read along with their own comments, and Minne's graph database will, over time, reveal which sources touch on related topics, even ones the user wouldn't have connected on their own. Someone building a personal knowledge library over years can return to old notes and discover new connections to recently added ideas, since the graph links them automatically based on shared elements. A research team self-hosting Minne gains full control over where the project's data is physically stored.

Pricing and business model

Minne is a completely free, open-source project under the AGPL-3.0 licence — there's no charge for the code or for using it. Because the app is meant to be self-hosted or run in a Docker container, the only real cost is the infrastructure needed to run it — the server it runs on and the time spent configuring it.

Limitations and what to watch for

Self-hosting means the user takes on responsibility for updates, backups, and the security of the instance — more administrative work than a ready-made cloud service maintained by an outside company. The graph-based, Zettelkasten-inspired approach also takes some getting used to for people accustomed to traditional, hierarchical folder systems — the learning curve tends to be steeper than with a simple notepad.

AI notes as input material for the graph

Minne's graph database shows its value best when it's regularly fed new notes — and ai notes, produced from a conversation with an AI model on some other topic, can be one source of that material if the user manually pastes it into the system. Minne itself doesn't generate content from AI conversations; it focuses on organizing and connecting what's already been saved.

What to check before choosing

Before committing to self-hosting Minne, assess your own administrative skills — keeping an AGPL-3.0 instance secure and up to date is an ongoing responsibility, not a one-time setup. It's also worth checking how the app handles importing existing notes from other systems if you're migrating from a previously used tool. People who already keep ai notes from conversations with AI models elsewhere should plan how those ai notes will make it into Minne's graph, since import isn't automatic.

In everyday practice

A research team self-hosting their own Minne instance gains confidence that the entire project knowledge base stays on their own infrastructure, without handing it to an outside cloud provider. People who regularly export their ai notes from AI-model conversations into Minne build one coherent graph linking both their own thinking and valuable AI-generated answers, making it easier to spot connections between them.

It's worth adding that the Zettelkasten method underlying Minne has a long history reaching back to analog card catalogs from before the computer era — a digital, graph-based implementation of the same idea shows that the underlying concept of linking notes proved universal enough to survive a change of medium spanning decades.

Position among PKM systems

In the personal-knowledge-management category, Minne competes with better-known commercial tools built on a similar philosophy of connections between notes, but stands out for its fully open code and the self-hosting requirement stemming from the AGPL-3.0 licence. That approach attracts users who value independence from an outside vendor more than the convenience of a ready-made cloud service configured for them.

Comparison with SumizAI

Minne and SumizAI take two different approaches to building a personal knowledge base. Minne relies on a graph of connections between manually written notes in the Zettelkasten spirit, requiring self-hosting. SumizAI generates ai notes directly from a conversation with an AI model and saves them as plain Markdown files in a vault the user owns, with no need to run your own server. Someone running an elaborate network of linked notes in Minne could treat their ai notes from SumizAI as one source of material to feed into that graph — AI answers worth remembering landing first in SumizAI, then manually connected to the rest of the knowledge base in Minne. Anyone who wants to build their own Zettelkasten-style connection graph on their own server will pick Minne; anyone who wants ai notes from AI conversations to appear automatically as files ready for further use will find that in SumizAI.

What SumizAI is

A note-taking application built around a conversation with an AI model. You ask a question, the answer streams back, and the answers worth keeping become Markdown notes — filed into a vault that is a folder on your own disk.

A vault is a directory holding base.md, a generated table of contents up to six levels deep, and a notes/ folder with one .md file per note. Before a note is written it is checked against the ones already there, so the fourth note about the same idea gets merged instead of added. Links between notes are ordinary Markdown links to files that exist.

The model is never ours: you bring your own API key to one of seven providers — Anthropic, OpenAI, Gemini, Groq, OpenRouter, a local Ollama or your own server — and pay that provider directly. A question sends the table of contents plus at most five relevant notes within a 24,000-character budget, and the app shows you which five it used.

Every answer kept this way becomes one of these ai notes, ready to search again months later without hunting back through old chats.

Side by side

Where they differ

• AlternativeTo's description of Minne does not mention an AI model. That is the whole starting point in SumizAI: you have a conversation with a model on your own API key, and the answers worth keeping become notes without you filing them.
• Minne is open source (AGPL-3.0), and SumizAI is not. If reading the source is what decides it for you, that is a real argument for Minne. The guarantee SumizAI offers instead is structural rather than legal: the notes are Markdown files in a folder you chose, so they open in any editor whether or not the application is running.
• AlternativeTo's description of Minne does not mention Markdown, so check what format your notes end up in before you fill it up. SumizAI writes standard .md files to a folder you picked, and an unpaid account can still export all of them.
• Minne is described in terms of linking notes together. SumizAI links them too, but deliberately without a syntax of its own: a link is an ordinary Markdown link, [Title](file-name.md), and the model may only point at a file that actually exists. There are no wiki-style [[…]] links to lose on export.
• Minne can be self-hosted. SumizAI has nothing to host on the desktop — the vault is a folder on your machine — and if you want the model on your own hardware too, a local Ollama is one of the seven providers it speaks to.
• AlternativeTo lists no mobile version of Minne. SumizAI runs on macOS, Windows, iOS and Android.
• Both are run from the EU: SumizAI's operator is registered in Poland and the servers are in Germany.

Which one to pick