engomez

Give us a follow on X: @openknowledgeai, we'll post updates there. Or feel free to dm me at @nickgomez and I'll reach out when available.

We support most things except bases at the moment. Let us know if you see any gaps that are important for you.

CLI is cross-platform, works on Linux/Windows. We've tested it but the environments can vary, so definitely let me know if see any issues.

Re:front-matter, we do optimistic parsing of it, haven't seen any issues with it. If we detect invalid markdown we return warnings to the agent in the MCP response so it knows it needs to fix it.

Got it, we'll investigate.

Could you share more on what's important for you there?

Ack, thanks for feedback ! We're definitely looking at a more integrated experience.

The external agents can open the open knowledge web viewer within their own embedded web UIs.

Within the OpenKnowledge app itself, right now we do support the Claude terminal embedded inside - try that out. We're looking at adding more within-app capabilities soon.

Appreciate it. Editor should already be pretty "Notion-grade", more to do though.

What functionality is most important to you re:Notion?

Haven't tried it, will take a look.

High level general purpose "IDE" for document editing (think Google Docs, Notion), that also exposes MCP/Skills for LLM wiki/second-brain scenarios.

Seems Rowboat is more focused on the personal assistant angle, we defer to your own agent (Claude, Codex, etc.) to do the LLM work.

Keeping the MCPs/skills cross-compatible across the different harnesses, and also getting non-eng folks familiar with git.

We wanted to make our own editor experience, allows us to do things like proper WYSWIG editing (Notion-like editor). MCP/AI integrations were one piece.

Our bar was "Notion-grade", i.e. drag and drop blocks, slash commands, select to highlight/bold, etc.

I don't think I'd seen an extension that does that. It was a technically very hard problem, rich text editors usually use a lossy intermediary format (e.g. prosemirror).

Got it, investigating.

(We're same team behind Inkeep -- already have a healthy biz).

Don't ask our VCs. Kidding -- we're taking a look at what would make sense for a cloud solution. E.g. richer team collaboration, etc.

Got it, makes sense. And neat ideas for the virtualization, will take a look.

Yup, we're working on it, should have integration eod or tomorrow.

Ack !

re: Web app do you mean local web UI, or web hosted?

Integration with local models/harnesses is top the queue. What IDE or Harness do you use?

We're looking at OpenCode/Zed next but open to input.

OpenCode is next on the queue. Each has it's quirks, just working through quality testing each.

Looks very relevant, will take a look. Definitely looking at built-in-chat-ui, thinking about how to integrate with the harnesses.

Appreciate it !

Gotcha. We're optimizing for the same scenarios, may be worth a look at our implementation in case transferable to yours. See:

#1 - the "autosync" and GitHub integrations do exactly this.

#2 - The app auto-instals skills/MCP server configs for a few harnesses

#4 - We embedded agentic-search capabilities via the MCP server (e.g. we virtualize 'ls' and 'cat' so we can enrich it for the agent for better hierchical navigation).

It would make a repo in your own GitHub account. You can choose whether that repo is in your personal GitHub or your GitHub org. We'll make that clearer in the UX.

Feel free to ping me any additional feedback any time (here or @nickgomez on X).

The skills should be pretty progressive disclosure optimized but we'll do an audit.

Skills / MCPs are not hard requirement, they're tailored for the desktop agents to be able to leverage built in tools we make available for e.g. agentic search over the content and manipulating the open knowledge web viewer and editor.

That was our exact stated goal -- felt a lot of the same pain. Feel free to drop me any feedback here or @nickgomez on X.

Right on. We did a lot of the same and then had to deal with coaching everyone on the team how to do also set it up.

Large inspiration for OpenKnowledge was providing these flows out of the box.

We'll prioritize Hermes/OpenClaw guides next.

Feel free to drop me any feedback as you try it out - @nickgomez on X.

Same flow I had. We did a few things to make the flow easier, like making it easy for Claude Desktop to open the OpenKnowledge web viewer within its own web view. Also exposing things like vector search, etc.

Our goal was you wouldn't need a separate IDE and to work well with the coding agent desktop apps.

But alas -- markdown files on your local machine is indeed the way for being AI friendly.

Example of the functionality that's OK specific: we made it so that e.g. Claude Desktop (or Codex, Cursor) can open the OpenKnowledge web viewer within their own embedded web viewers, to make for better side-by-side editing. Since Obsidian is closed source, we wouldn't be able to make that work.

Making the skills/MCP specific to OpenKnowledge allows us to optimize experiences like that.