Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.remoteagent.chat/llms.txt

Use this file to discover all available pages before exploring further.

Yes. The agent runs as a process on your machine — it is the component that executes your AI runner and processes commands. If your machine is off or the agent process has stopped, the bot will not be able to run tasks.For always-on availability, run the agent on a server, a cloud VM, or a machine that stays powered. Use a process supervisor like pm2 or systemd to restart the agent automatically after reboots or crashes.
pm2 start "remoteagent start" --name my-project --cwd /path/to/project
pm2 startup
pm2 save
Start with claude-code — it uses the Claude CLI and gives you full Claude capability. If you already have Claude installed and authenticated, it works with no additional API key.If you want the lowest latency and are happy managing an Anthropic API key directly, claude-sdk runs in-process with no subprocess overhead.If you want a free option with no API key at all, try opencode — it supports 75+ providers including GitHub Copilot and local models, and works out of the box with no configuration.If you want a free option with Gemini models, try gemini — the Google Gemini CLI has a free tier. Note that it is currently in beta.If you need multi-model flexibility or want to use local models via Ollama, aider is the right choice. It requires Python.If you have a custom tool or internal AI gateway, use the custom runner.
Yes. Your API key is stored in ~/.remoteagent/agents/{agentId}.json on your local machine and is never transmitted to RemoteAgent.CHAT servers. The agent calls the AI model API directly from your machine. RemoteAgent.CHAT only sees the prompt you sent via Telegram, not the full conversation context or your credentials.For additional security, set restrictive permissions on the config files:
chmod 700 ~/.remoteagent
chmod 600 ~/.remoteagent/agents/*.json
Yes. Run remoteagent init in each project directory to register a new agent. Each agent gets a unique ID and appears as a separate entry in the bot and dashboard.The number of projects you can register depends on your plan:
  • Trial / Pro — unlimited projects
  • Solo — 1 project
When multiple agents are online, commands go to the currently active project. Send /projects to see the list and switch.
When the 14-day trial expires, your agents stop accepting commands and the bot notifies you. Your data — agents, session history, config files — is preserved in full.To reactivate, choose any paid plan from the dashboard or via the link in the bot’s trial expiry message. Your agents come back online within 30 seconds of payment confirmation, automatically.
Not currently. The relay infrastructure runs on RemoteAgent.CHAT’s managed stack. The relay is designed to be transparent — it does not inspect your code or store sensitive data beyond a prompt preview. The agent package itself runs entirely on your machine.
The bot sends you a Telegram notification immediately when an agent disconnects. The notification includes the project name and a timestamp.To bring the agent back online, run remoteagent start in your project directory, or by name: remoteagent start "project-name".To prevent unplanned downtime, run the agent under a process supervisor that restarts it automatically. See Offline alerts for setup examples.Offline alerts are available on all plans.
Run the reinstall command — it updates to the latest version and restarts any running agents automatically:
remoteagent reinstall
Your existing config files and paired agents continue to work after an update.
Not currently. Only the account owner’s Telegram user can send commands to agents.
Delete the agent from the dashboard. This immediately invalidates the agent’s credentials — it will no longer be able to receive commands even if the process is still running locally.To fully clean up, also stop the agent process on your machine:
remoteagent remove "project-name"
RemoteAgent.CHAT stores:
  • Your Telegram user ID and username
  • Your plan and billing status
  • Agent metadata: project name, last-seen timestamp, online/offline status
  • Session records: start time, end time, status, and the first 200 characters of your prompt
RemoteAgent.CHAT does not store:
  • Your API keys
  • Your source code
  • Full prompt or response content
  • File contents processed by the AI runner
The agent binary runs on Windows via WSL 2 (Windows Subsystem for Linux). Install WSL 2 and run the installer from within the WSL environment — no Node.js required.Native Windows support (PowerShell/CMD) is not officially tested or guaranteed. WSL 2 is the recommended path for Windows users.