Personal
For individual use
$19 / month
- 1 connector
- Up to 20 tools
- Up to 2 modules
- AI assistant connection
- Read-only by default
- Change confirmation
- Model gateway
AgentGate
AgentGate turns your systems into secure business tools for ChatGPT, Claude and any AI agent, and governs the models they use.
Risk
Employees paste information from your systems into a chat, with no control or record.
Gap
Databases and in-house systems are left out of standard connectors.
Cost
A custom project takes months and leaves code that someone has to maintain.
The connector is installed in your network and it is the one that starts the connection. Your systems never receive connections from the Internet.
Your team
ChatGPT, Claude or other assistants
AgentGate
Permissions, rules and audit
Connector
In your network, no inbound ports
Your systems
Databases and APIs
The connector starts the connection: outbound, encrypted and certificate-based (mTLS).
01
A Docker container in your network, with a guided installer.
02
Business questions about your systems, with the exact fields that are returned.
03
Each tool only for the people and groups it belongs to.
Your databases and APIs become tools that any compatible assistant can use.
See how it connects →A single access point to AI models, with budgets, per-person keys and security steps.
See the model gateway →01
The connector only opens an outbound, encrypted connection.
02
With the connector, your systems' passwords never leave your network.
03
Only predefined, approved and signed tools are executed.
04
Each tool is assigned to specific roles or groups of your organization.
05
Every tool that writes asks for confirmation before it runs.
06
Who queried what, from which client and with what result.
Direct mode (optional): if you prefer not to install anything, the platform can connect on its own to reachable systems; in that case the credential is stored encrypted in AgentGate.
All traffic to the models goes through a single point inside your network. You know who spends how much, you set limits and you keep sensitive data from reaching an external provider.
Questions and tasks that someone does by hand today and that an assistant can do with permissions and a record.
Ask your data questions in plain language, without giving free access to the database.
Let the agent make real changes, with confirmation and without repeating them.
Use AI with systems behind your firewall without exposing them.
Assistants that look up orders, statuses and cases with real data.
The same tools for Claude, ChatGPT and OpenCode, with the same permissions.
Know who spends how much on AI and set limits.
Keep personal data from reaching an external AI provider.
Turn an API you already have into tools for agents.
How AgentGate applies in different industries.
Ask an assistant about harvests, fields and stock, using the data where it already lives on the farm and in the plant.
Assistants that look up portfolio, transactions and compliance data without customer data reaching an outside provider.
Well, equipment and maintenance status within reach of an assistant, without exposing plant systems.
Production, fleet and safety data of the operation, available in plain language with permissions by site and role.
Start on your own or with your team, or book a demo for your company.
You sign up and subscribe in a few minutes.
For individual use
$19 / month
For small teams
$79 / month
We start with a demo and a pilot on your real case.
To start with one system
$240 / month
For several systems and teams
$690 / month
For the whole organization
Contact us
Prices are expressed in US dollars (US$). Reference prices, subject to confirmation.
Ask us about these add-ons.
Agents that work on their own with their own identity and quotas.
Connection of plants and industrial systems.
A platform that turns your databases and APIs into secure tools for AI assistants such as ChatGPT or Claude, and also controls access and model spend.
No. The connector is installed in your network and it starts an outbound, encrypted connection to AgentGate. There is also an optional direct mode that installs nothing.
With the connector, no: they stay in your network. In the optional direct mode, the credential is stored encrypted in AgentGate.
Only if you allow it. Every connector is read-only by default, and every tool that writes asks for confirmation before it runs.
Any MCP-compatible client. There are connection guides for Claude, ChatGPT and OpenCode.
It is a single access point to AI models: compatible with OpenAI and Anthropic, with budgets, per-person keys and steps such as personal data masking.
Tell us your case and we will show you how it would look with AgentGate.