Skip to main content

Bowrain

Bowrain is the context graph your people and agents plug into: the coordinates that fix voice and tone for a specific time, place and audience, recorded in a form a machine can read. Profiles, vocabulary and content memory are held on a server and shared across every project, person, and agent, with collaborative editing, review, automation, and version history around them.

New to the idea? Start with The context graph: what a profile is, what coordinates are, and why a rename is one decision and five different rules.

Content reaches a workspace from the systems it already lives in. A content platform, a design file, a code repository, and a developer's checkout are peer routes in, and everything is ordinary project content once it arrives: same governance, same review, same history.

A team shares one workspace through a browser and a native desktop app. The hub, the editor, review, presence and history all live on the server.

Outdated wording

The narration uses terminology that has since been retired. The interface and the behaviour shown are unchanged.

What Bowrain adds​

Shared, versioned governance​

Profiles, vocabulary, and content memory held on the server and shared across everyone, writers, reviewers, and AI tools alike, instead of living in each person's checkout. Changes are versioned and auditable: who approved a term, when a profile changed, what a piece of text used to say. And the context learns: repeated corrections become versioned, enforced rules, so what a team discovers by correcting real output is captured instead of lost. See Voice and corrections.

Governed review​

A run drafts and checks and parks what a machine cannot decide; a person promotes it in one review session across items and locales, and the decision is recorded against the workspace. Review decides what a locale can ship as, and the last approval starts the run that delivers.

Collaboration​

A web editor and a desktop app connect to the same server. People work in Visual and Table views with the checks, the terms in force and the content memory in context; edits, presence, and live updates propagate to every client without a refresh. See Real-time collaboration.

Connectors​

A workspace syncs against the systems content already lives in: a content platform (WordPress, HubSpot), a design tool (Figma), a code repository (GitHub, GitLab), or a developer's checkout (kapi). Most run server-side, with no local checkout: source flows into the governed workspace, gets drafted and checked, and publishes back to where it came from. See Connectors.

AI that knows where it is​

The workspace's governed vocabulary, content memory, and voice checks are the context an AI agent reads, over MCP, so generated and adapted copy is on-voice from the first draft, and corrections flow back into the shared, enforced checks.

Automation​

Server-side rules run flows when content arrives, a language stops meeting a ship gate, or a review completes: shared, event-driven workflows for the whole workspace. See Automation.

Stewardship over time​

A persistent, versioned content store keeps the history of every block, branch, and language, so the work compounds: vocabulary decisions, voice corrections, and remembered text stay with the project as people and tools come and go.

How it fits together​

Content sourcesCMS · design · repository · checkoutBowrain workspacegovern · automatePeople & agentsweb / desktop / MCPbring source ina connector fetch, or a pushdraft, check, gateserver automationdeliver for reviewlive-sync to web / desktopreview & approvein the sessionapproved editsback to the workspacepublish backto the source system

Content flows in from any connector, the server governs and automates, people and AI tools review, and results publish back to where they came from.

Parts of the platform​

  • Server: workspaces, authentication, the versioned content store, automation, and the connectors.
  • Connectors: content platforms, design tools, code repositories, and a developer's checkout. Most run server-side with no checkout involved; see Connectors.
  • Web app: the Context hub, the review session, and a browser-based editor with Visual and Table views.
  • Desktop app: a native cross-platform client with offline support.

What's next​

One graph, two scopes​

Bowrain is built on kapi, the Apache-2.0 toolchain that holds the context graph for one project and runs on its own, directly on files, with no server or account. Nothing is withheld from it. Reach for Bowrain when the graph has to reach further: several projects, several surfaces, hosted review, or a team working together.