How is this different from ChatGPT?
ChatGPT is a chat in a browser or an app. CapyAgent runs on your side: it remembers you between conversations, runs jobs on a schedule, writes first in Telegram only to chats you named, and works with your business systems. History and notes stay on your machine. You choose the model, including a ChatGPT subscription, which connects with a code from your phone.
Can I run an AI assistant on my own server?
Yes. The agent installs on your server with one command and runs around the clock as a service. You need a server with Ubuntu or Debian and 2 GB of memory or more, and access to a model: a subscription, an API key, or a model on the same server through Ollama or LM Studio. If you would rather not keep a server, there is the cloud: a separate server for the agent at 1,590 RUB a month.
What do I need to start?
A server or a computer, access to a model, a Telegram bot. Root is not required: the same command installs into your home folder.
How much does it cost per month?
The program is free: install it for yourself or inside your own company and pay nothing for it. You pay only your model provider, for your own subscription or API key. In the cloud the server for the agent costs 1,590 RUB a month, the model is paid separately straight to the provider, about 2,000 RUB a month, so about 3,600 RUB a month together. There is no online payment yet: we send an invoice after your request. Setup help and support are sold separately, see the
Pricing page.
Where is my data?
On your machine: history, notes, tasks, settings. Only what you connect leaves it: the request to the model and any service whose keys you added. No telemetry. Voice notes are transcribed on your machine, audio is not sent anywhere.
Which models can I use?
A ChatGPT subscription (sign in with a code from your phone), any OpenAI-compatible endpoint (OpenRouter, DeepSeek, Qwen, Kimi and others), an Anthropic API key, Gemini, plus a model on your own machine through Ollama or LM Studio. A Claude subscription cannot be used in place of an API key.
Do I need a VPN?
The wizard checks Telegram and your model with a real request. If one of them does not open from your server, it offers a proxy, or our VPN+ subscription, which carries only Telegram and the model, not the whole machine.
Can I run it without a server?
Yes. Install the desktop app on Windows, macOS or Linux, or run the same command on your own computer. One catch: while the computer is off or the app is closed, the agent is silent and schedules do not fire. To run it around the clock, put it on a server or take the cloud.
How do I update?
On your say-so: the agent does not look for updates on its own. Run sudo CAPYAGENT_UPDATE=1 /opt/capyagent/bin/capyagent update. It keeps the previous version and your data first and rolls back on failure.
Is it safe?
Anything that gives access to the machine (commands, files, screen capture) is off after install. A risky action runs only after a one-time "yes" that names the action. Destructive ones (wiping the disk root, a fork bomb) are refused in any mode. Strangers cannot message the bot. The limits live in code, not in a request to the model.
What does it not do?
It does not listen to your microphone. It does not watch your habits to make suggestions. It does not pay for you or use your bank. It writes first only to chats you named in advance, and no more often than the limit you set.
Can two people or a whole team use one agent?
Yes, add them to the allow-list. Each gets their own conversations, while memory and access are shared in one agent. If they must not be shared, run a separate instance.