Show HN: Toolchestrator – make local, AI-built tools usable by your team

Toolchestrator: the runtime for vibe-coded apps Sound familiar? AI made building apps easy. It didn't make them usable by anyone else. Born on a laptop, stuck on a laptop Someone builds a genuinely useful tool in an afternoon. It works, for exactly one person, on exactly one machine. Nobody else can see it, use it, or even knows it exists. The same tool, built three times Finance has an invoice tracker. So does Ops. So does that one PM. Three versions of the truth, none of them talking, because nobody could see what already existed. Data locked in one person's terminal The numbers your team needs live inside a database file on one laptop that goes to sleep at 6pm. Moving it all to “real infrastructure” is a project nobody has time for. How it works Three steps. No migration. Nothing to deploy. Your AI copilot does the wiring. You just tell it to. 1 Build your app A script, a command-line tool, a little web app, vibe-coded with Claude Code or any AI copilot and running wherever it already runs. Toolchestrator never asks you to move or rewrite it. 2 Tell your copilot Give it your hub address and a personal token from your workspace settings. Your hub serves the full connect guide and the client. Your copilot fetches both and does the wiring. 3 Your team uses it The tool appears in your workspace: its story, its data, its buttons. Teammates browse the data, run its actions, even open its full app or terminal, all from their browser, or straight from their AI chat, with nothing to install. You, to your copilot “Connect this tool to Toolchestrator.” Want the full walkthrough with screenshots? Follow the step-by-step guide. Curious what it will do? Read the connect guide your hub serves, every step in the open, or download the skill. What you get The runtime that makes lone apps a team AI-native Your tools, inside any AI chat The part that makes it infrastructure, not a dashboard. Connect the hub to Claude, or any MCP client, and your AI discovers your team's tools, reads their shared data, and runs their actions, with exactly your permissions. Set it up in a minute. A living registry Every connected tool announces what it is, who built it, and which problem it solves, so the next person searches before they rebuild. Notes on tools and models Leave a note on a tool, or pin one to a specific data model: how to run it, what not to touch on a Friday, the gotcha that cost someone an afternoon. Team knowledge that lives next to the tool, not lost in chat. Shared, queryable data Tools publish the records worth sharing. Teammates and other tools read them with filters (“open invoices over €1,000”) straight from the hub, even when the source machine is asleep. Run actions from the dashboard Every tool lists the actions it can perform. Pick one, press Run, see the result, executed on the owner's machine and delivered to your screen. Use full apps in the browser If a tool has a web interface, teammates open it with one click and use it as if it ran on their own machine. A floating switcher hops between your team's apps. Terminal apps, streamed live Built a TUI or an interactive command-line tool? Serve it through the hub and a teammate drives it live in their browser, keystrokes and all. The program still runs on your machine, and only the screen travels. The data map A live picture of your tool ecosystem: which tools feed which, who reads what and why. Drawn from real usage, not wishful documentation. Fields that won't silently break When one tool's data feeds another, those fields become a contract. If an AI edit would remove or change one, it's flagged with exactly which teammate's tool breaks, before it happens. amount · read by Reorder Planner Pipelines & change alerts Chain tools into multi-step flows, or let one tool react the moment another's data changes. Orchestration without scheduled scripts to babysit. Offline is a state, not a failure Machines sleep. Work queues. When a tool comes back online it picks up whatever was asked of it, and everyone can see, live, what's reachable right now. Sharing you control Every tool starts private. Its owner decides: keep it personal, share with a department, or open it to the company. One switch governs the data, the actions, and the app. Who it's for Built for the people actually building Vibe coders You ship little tools weekly with your AI copilot. Now each one gets an audience: your team can use it, other tools can build on it, and your copilot warns you before an edit breaks something a colleague relies on. Product & project managers You don't need to write the tools. You just need to see them. One dashboard shows what exists, who owns it, what data flows where, and lets you run the things you need without asking anyone. Ops, finance & everyone else Use the team's tools from a browser like any web app, with no installs and no terminal. The spreadsheet-replacing tracker your colleague built is finally something you can open too. AI-native runtime Ask your AI about your own tools Connect the hub to Claude and it can list your team's tools, read their shared data, and run their actions, all with exactly the permissions you already have in the dashboard. Two ways to connect, each about a minute. Claude web & desktop app Add it as a connector In Claude, open Settings → Connectors and choose Add custom connector. Paste your hub's MCP address: Connector URL https://hub.toolchestrator.com/mcp Leave sign-in required, let Claude register a client automatically, and add it. The Toolchestrator sign-in page opens: sign in, approve, and you are connected. Claude Code & other MCP clients Add it with a token In the dashboard, open Settings → AI chats (MCP) and create a token. Run one command (the dashboard shows it with your token filled in): Terminal claude mcp add --transport http toolchestrator \ https://hub.toolchestrator.com/mcp \ --header "Authorization: Bearer tcm_your_token" Ask your AI: "list my Toolchestrator tools" and go from there. Your AI sees exactly what you see, never more. It reads shared data and runs actions as you, and you can revoke any connection from Settings at any time. Security Connected, not exposed The whole design starts from one rule: nothing ever connects into your machine. Outbound-only. Tools call out to the hub and poll for work. The hub never opens a connection into anyone's laptop. There's simply no door to knock on. Private by default. A new tool is visible to its owner alone. Widening to a department or the company is a deliberate owner decision. The dashboard warns before company-wide sharing, and the copilot workflow flags personal-looking data. Every member approved. Joining a workspace takes an invite code and an admin's approval. Until then, a new account can't see anything at all. Workspaces are walls. Companies are fully isolated from each other. Inside one, access is re-checked on every single request. Narrow a tool's sharing and everyone outside the new scope loses access mid-click. An audit trail, built in. Who connected what, who ran which action, who opened whose app: the activity feed keeps the receipts. For IT, security & ops leads Shadow AI is already here. Now you can govern it. Your people are building AI tools whether you approved it or not. Toolchestrator gives you the registry, the audit trail, and the access control over what is already running. See what exists Every AI-built tool your team connects announces itself: what it is, who owns it, which data it touches. The invisible scripts on someone's laptop become a registry you can actually read. Prove what happened Who connected what, who ran which action, who opened whose app or console. A workspace activity log keeps the receipts, and platform admins get a metadata view across every workspace, records excluded by design. Control who can touch it Private by default. Every new member is admin-approved. Sharing is scoped to a person, a department, or the company, and re-checked on every single request. Outbound-only. Tools connect out to the hub and poll for work. Nothing ever opens a connection into an employee's machine, so there is no inbound attack surface on your endpoints. Your hub, your domain. Self-host the hub or run it white-labeled on your own subdomain. The client is hub-agnostic and the code stays in your control. SSO / SAML is on the roadmap. Today, access is per-workspace accounts with admin approval. Tell us what your rollout needs. Talk through your rollout FAQ Fair questions Do my tools move to the cloud? No, that's the point. Your tools keep running exactly where they run today. They connect outward to the hub to share what you choose to share: their description, their data models, selected records, and the actions they can perform. What happens when the laptop running a tool is off? The data it already shared stays available on the hub, so teammates can keep reading it. Anything you ask the tool to do waits in a queue and runs when the tool comes back online. The dashboard shows live which tools are reachable right now. What do my teammates need to install? Nothing. Teammates use everything (browsing data, running actions, opening tool apps) from the browser. Only the person connecting a tool needs their AI copilot for the one-time setup, and the hub itself serves the copilot the full connect guide and the client, so there is nothing to distribute. Which AI assistants and languages does it work with? It's built for AI coding copilots (Claude Code first), but the connection is a small client library published for both Python (pip install toolchestrator) and Node (npm install toolchestrator), so any assistant (or human) that can run Python or Node can connect an app. The two clients speak the same hub API, so a Python app and a Node app sit side by side in one workspace. Your hub also serves the Python client and a step-by-step connect guide directly. What about sensitive data? Every tool starts private. Sharing wider is an explicit owner decision, and the copilot workflow warns before company-wide sharing when records look personal. Secrets and credentials are never meant to be synced. The hub is a collaboration layer, not a secret store. Access is re-checked on every request, and joining a workspace requires admin approval. Can one tool break another? Not silently. The hub tracks which fields of your data other tools actually read. If an edit would remove or change one of those fields, the change is flagged with exactly which tool depends on it, so your copilot stops and asks instead of quietly breaking a teammate's workflow. What does a “tool” even mean here? Anything small and useful: a script that parses invoices, a stock tracker that runs in a terminal, a tiny web app for quotes. If it can run Python next to it, it can join the hub: no rewrite, no framework, no deployment. Give your vibe-coded apps a runtime Create a workspace, invite your people, and connect the first app with one sentence to your copilot. Create your workspace Already have one? Sign in · New here? Follow the guide