Docs
How belleq works.
belleq sits between your tools and your AI. Connect your tools once, group them into contexts, and give any AI exactly the right access — with memory that follows you across assistants.
Introduction
Modern AI assistants are most useful when they can reach your real tools — your docs, your issues, your designs. But wiring each assistant to each tool is repetitive, hard to scope, and locks your setup to whichever AI you used last.
belleq is a single layer that holds your connections and your memory. You connect a tool once, organize tools into contexts, and hand any AI a single link. The AI sees exactly the tools that context allows — and belleq quietly remembers what matters so it's there next time, on any assistant.
Connect once
One secure login per tool, reused everywhere.
Scope precisely
Each context exposes only its allowed tools.
Stay portable
Memory and contexts live with you, not the AI.
Quickstart
Four steps from zero to an AI working inside the right context.
Connect a tool
In the dashboard, open Connectors and add a tool — Notion, Linear, GitHub, and more. You log in once; belleq keeps the connection so you never set it up again.
Create a context
Create a context for a project, role, or task — for example design or support. Choose which connected tools that context is allowed to use.
Point your AI at it
Each context has its own link. Add it to Claude (or any AI that supports connections) as a custom connector. Your AI now sees exactly that context's tools — nothing else.
Switch any time
Moving from design work to a code review? Switch to a different context's link. The tools, knowledge, and memory change with it — no reconfiguring.
Core concepts
Four ideas cover everything belleq does.
Connections
A tool you've connected once — Notion, GitHub, Linear, Slack, Figma. Connections are unlimited on every plan and shared across all your contexts.
Contexts
A named profile that decides which connections an AI can use. Each context has its own link and its own memory. Create one per project, role, or person.
Knowledge base
belleq learns from how you use AI — what you share, what it fetches, what you decide — and surfaces it when useful. No manual tagging or upkeep.
Cross-LLM memory
Your contexts and memory belong to you, not to one AI. Point Claude, ChatGPT, or Grok at the same context and everything is still there.
Connect a tool
Open Connectors in the dashboard and choose a tool. You'll sign in to that tool once through its own secure login — belleq never sees your password, and stores the connection encrypted. From then on the connection is available to every context you create; there's nothing to re-enter.
- Connections are unlimited on every plan.
- A connection is shared across contexts — connect Notion once, use it anywhere.
- Revoke a connection at any time; every context that used it updates instantly.
Create a context
A context is a named set of tools for one job. Create one for design, another for support, another for code-review. For each, pick which of your connections it's allowed to use. The AI pointed at that context will see those tools and nothing else in your workspace.
Every context gets its own stable link in the form:
mcp.belleq.app/c/your-contextConnect your AI
belleq speaks the Model Context Protocol (MCP), so it works with any assistant that supports remote connectors. Add a context's link as a custom connector and authorize once.
Claude
Settings → Connectors → Add custom connector. Paste your context link and authorize. belleq's tools appear in any new chat.
ChatGPT
In a workspace that supports custom connectors, add the context link as an MCP server. Your context's tools become available to the assistant.
Cursor & others
Any client that supports remote MCP servers works. Add the context link as a server URL — no keys to copy, the connection is already authorized.
No MCP support? Use the REST API
ChatGPT, Gemini, and your own code can reach the same context over plain HTTP with your context API key — read the REST API docs.
Knowledge base
As you work, belleq watches the exchange between you and your AI — the documents you share, the answers it looks up, the decisions you reach — and captures what looks durable into the context's knowledge base. There's nothing to tag and nothing to maintain.
When a later conversation touches the same ground, belleq surfaces the relevant knowledge automatically. Important things stay close; stale things fade. Because the knowledge lives in the context, it's there whether you return on Claude, ChatGPT, or anything else.
Access & sharing
A context is a scope. Share one with a teammate and they get exactly those tools — never the rest of your workspace. Each context keeps its own memory and a clear record of what the AI saw and used, so access stays accountable.
Scoped sharing means you can hand a contractor a single context for one project and trust that it can't reach anything outside it — no broad workspace access, no copied credentials.
FAQ
Do I have to set up each tool every time?+
No. You connect a tool once. After that it's available to any context you choose — no re-connecting, no re-configuring.
What happens when I switch AI tools?+
Everything stays. Your contexts and memory live with belleq, not with whichever AI you used last. Point a new assistant at the same context and it's all still there.
Does it remember things on its own?+
Yes. belleq learns from how you actually use AI and surfaces what's useful. There's nothing to tag or maintain.
Can different people get different access?+
Yes. Each context is its own scope. Share one with a teammate and they see only those tools — never the rest of your workspace.
Ready to try it?
belleq is in private beta. Join the waitlist and we'll invite you to connect your first tool and add a context to your AI.
Join the waitlist