Obsidian Vault to Enterprise Company Brain: Where Agents Write, Branch and Merge
Summary
The post argues that personal knowledge tools like Obsidian hit fundamental limits at enterprise scale: no multi-user writes, untyped free-form text, and no automation. The author proposes an 'enterprise company brain' built on typed graphs, git-style branching for agent writes, and open object storage. Agents write knowledge to their own branches, with auto-merge for non-conflicting changes and human review required for conflicts. The author showcases this with OmniGraph, rebuilding a personal Obsidian CRM into a typed graph with enforced schemas and agent-driven updates. The core thesis is that open files with types, history, and a merge workflow let knowledge outlive any single tool or curator.
Key Insight
Scaling personal knowledge management to enterprise requires typed graphs with git-style agent branching—replacing free-form linked notes with structured, versioned, open-format knowledge that many agents can write concurrently while humans resolve conflicts before anything merges to the canonical record.
Spicy Quotes (click to share)
- 5
Without that, a company brain fed by agents drifts into noise.
- 2
Nothing lands on the 'real' version until it's approved.
- 4
Branches are what make 'continuously updated' and 'still correct' work together.
- 6
There's no silent last-write-wins.
- 7
Open files outlive every tool that reads them, and a company brain stored as open files in your own bucket will survive whatever CRM or wiki is used today.
- 7
My Obsidian vault needs me, the single user. An enterprise company brain...mostly needs someone to hit 'merge'.
- 3
A design from first principles for agents that need lots of interconnected, real-world knowledge combined with our data is essentially a graph, not a tabular format.
- 4
It's not only embeddings you search by similarity, but also typed, declared knowledge plus inferred similarity, versioned like code, so a hundred agents can write to it while humans keep it from drifting into noise.
Tone
technical, visionary, practical
