ProDocStore publishes private staff and customer docs from GitHub. Ask AI to update a page, review the diff, then apply through GitHub. No CMS body editor, no hidden source copy, no manual text changes outside source control.
Teams write docs in READMEs, wikis, notes, tickets, and chat threads. AI can help maintain them, but only if the source is inspectable, reviewable, and published in a format both humans and agents can read.
A customer account can have useful docs split across Markdown, GitHub issues, generated pages, and old website folders. Readers and agents need one published surface.
Most docs platforms make editing easy but review weak. ProDocStore keeps GitHub as the source of truth so every change has history, authorship, and rollback.
ProDocStore lets AI draft a replacement, but humans review the diff. If a person wants to hand-edit, they do it in GitHub rather than a separate CMS.
Private KBs should ship search, sitemaps, `llms.txt`, and scoped MCP metadata so agents can cite and update the right source.
ProDocStore publishes GitHub repositories that use Markdown in docs/ and a zensical.toml config. Each KB deploys to its own Cloudflare Pages project and can attach custom domains.
Each customer KB starts as a Zensical Markdown repo with its own Pages project, workflow, and domain target.
ProDocStore keeps Markdown source in GitHub. Zensical builds it from Markdown, and Cloudflare hosts the generated site.
The editor is a proposal surface. People describe the change, AI drafts the replacement, and the final manual intervention happens in GitHub where branch protection, review history, and blame stay intact.
Use natural language to update a page, add policy detail, tighten an explanation, or convert notes into publishable docs.
The UI shows the current source, the AI replacement, and a line-level diff. It does not expose a manual content editor.
If a human needs to touch text by hand, the editor opens the GitHub file editor for the target path.
The browser extension uses the same rule from a live docs page: prompt, preview, then Apply through GitHub.
The loop is intentionally narrow. ProDocStore is not trying to replace GitHub; it makes GitHub-backed docs easier for humans and AI agents to maintain.
Connect a public Zensical repo, choose the docs folder, and publish through Cloudflare. Source files remain in the repository where review, permissions, and history already exist.
Ask for a rewrite, new page, cleanup, or structure pass. The editor creates a proposal and diff, not a hidden mutation.
Free public KBs are built by Zensical with generated search, sitemap, metadata, and future MCP discovery.
Register the GitHub repository and docs path. ProDocStore reads source from GitHub instead of storing a second copy.
Build the Zensical project with navigation, search, sitemap, and agent-readable metadata.
Use the web workbench or extension to request changes. The AI produces a proposal and diff, then GitHub handles manual review.
Publish `llms.txt`, source metadata, and future MCP discovery so agents can find and update the right pages.
<!-- Written 2026-04-23. Approved by @sergey. --> <article class="doc"> <h1>Session flow</h1> <p>Sessions are issued as signed cookies. Rotation happens on every privileged action.</p> <h2>Invariants</h2> <ul> <li>No token in localStorage.</li> <li>Cookie is httpOnly and SameSite=Lax.</li> </ul> </article>
Agents need current source, clear context, and permission boundaries. ProDocStore gives them public docs to read and a proposal workflow for updates.
Published pages, search data, sitemaps, and future `llms.txt` output give agents a reliable place to retrieve the current explanation.
The editor gives AI enough source context to propose a full replacement while keeping apply/review in the user's hands.
Every accepted update can become a commit or PR. That keeps history, blame, branch protection, and rollback where teams already work.
FreeDocStore handles open/public KBs. ProDocStore is for closed staff and customer knowledge bases.
The ProDocStore MCP server exposes account workspace visibility, registered KB metadata, Zensical validation, deploy checks, and publish planning. Write tools run behind auth.
Connect agents to the production ProDocStore MCP endpoint.
Agents can discover the MCP server from the platform's well-known metadata.
Use the console or extension to start from a GitHub-backed Zensical repo. ProDocStore is the private/customer pair to FreeDocStore.