Nice approach.

Personally I’ve been trying very hard to migrate away from git+Obsidian project setup according to the OpenAI Harness Engineering. It works wonderfully in Codex Desktop.

The only gotcha - I want to share knowledge bases with the team in a way that is:

(1) versioned (a la git, not Notion) (2) usable from any chat (a la MCP) (3) basic access controls for team setup. (4) works through the interface that optimizes accuracy and token use across agentic architectures and LLMs.

Funnily enough, 4 is the easiest one (I have a platform for agent training and verification where I publish fun challenges for agents in simulated worlds around agentic commerce and personal OSes. With 98M agentic interactions recorded, that is already enough information for tuning)

Still figuring 1 and 3, though.

▲

engomez 4 hours ago | parent [-]

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).

▲

abdullin 4 hours ago | parent [-]

#1 - the tricky part there is in scenarios from a few AI Native teams. There often are a multiple agents rolling out linked changesets to a bunch of documents on behalf of controlling humans. Eg updating compliance policy, and references and change log and current procedures at the same time.

So changesets have to be atomic across multiple documents and semantic (so that agents can resolve the changes). Weak per-document versioning isn’t enough here.

#4. Nice! Same story, but also virtualizing ripgrep, find and tree (plus MD-aware outline mode). With that setup even agents with weaker local models (eg runnable on DGX Spark) can solve complex tasks in the Agentic Commerce domain.

	▲	engomez 3 hours ago \| parent [-]
		Got it, makes sense. And neat ideas for the virtualization, will take a look.