Gluesync Enterprise Brain · Extend
The brain grows in two directions. Skills capture the procedures your agents discover and make them reusable, versioned, and immutable. Company tools bring GitLab, Notion, and any approved MCP server into the same governed loop, registered while in platform, refused everywhere else.
How it works
Discover
Grounded in the schema graph and shared memory, a Spark agent works out which tables, joins, and filters answer the question, and which approved tools it needed along the way.
Publish
With the publish_skill capability the agent freezes that procedure as an immutable, versioned skill. The transcript links to it; the Build & publish workspace highlights it for review.
Reuse
Attach the skill to any published agent without cutting a new agent version. Managers, Super admins, and keys with the skills:publish scope decide what the company keeps.
Capabilities
Everything the brain learns stays inspectable: a skill is text and contracts, a tool bundle is a named list of remote tools, and both carry provenance and a version.
Skills
Instruction, knowledge, and tool-bundle skills are referenced by slug and version from one or more published agents.
Company tools
Register GitLab, Notion, or any HTTPS MCP server while in platform. Discover its tools, choose the ones you want, and publish them as a tool bundle.
Memory
When a run or a conversation completes, the input and the tool trace are sedimented into a memory candidate and queued off the request path.
FAQ
No. publish_skill requires the caller to be a Manager or Super admin, or a platform key that carries the skills:publish scope. The published skill appears in Build & publish with a version, a content hash, and the run or conversation that produced it.
Any MCP server reachable over HTTPS: GitLab, Notion, an internal ticketing system, a document store. You register the URL and its allowed hosts, discover the tools it exposes, and bundle the ones you want. Nothing outside the allow-list can be called from a run.
They are always treated as writes. A run that wants to call one parks until a signed-in user approves it; API keys, personal tokens, and schedules cannot approve on their own. The bearer secret comes from a vault reference, and unregistered hosts are refused before any request leaves Core Hub.
Anyone who can see a shared memory can forget it, and every user can forget or make private their own. Memory never contains result rows or credentials, so the worst case is a stale route, not a leaked value.
Enterprise brain
The foundation for every AI tool your company uses, built on the databases Gluesync already integrates.
Explore → Connect Connect your AI toolsPoint Claude, ChatGPT, Grok, Meta Muse, Hermes Agent, OpenClaw, or Cursor at Core Hub and let them ask the brain under the caller's permissions.
Explore → Own Ownership and privacyA dedicated brain database on your infrastructure, memory shared by default and private on request, never rows, never secrets, never SaaS.
Explore →Gluesync Enterprise Brain
Skills make one good answer repeatable. Company tools make the brain reach beyond the database. Both stay versioned, approved, and yours.
