A teammate, not a chat window.
A chatbot answers while you watch. A JamBots bot keeps going after you leave: it remembers what it learned, runs routines on a schedule, uses its own cloud computer with a browser and desktop, and messages you when it has a result, a question or an action that needs your approval.
Persistent bots
A bot is a continuing teammate with one conversation that never resets. Give it a name, an avatar and standing instructions, then talk to it like a colleague. Change its settings by asking it in chat.
- One continuous thread with messages, progress, results, questions and approvals
- Send a message while it works and it folds that into the current run
- Stop a running bot at any time
Memory you can edit
Each bot writes down preferences and facts as it learns them. Read, edit and delete any entry, see the revision history and roll back.
Routines
A routine is a prompt with a schedule: one time, every interval, or cron with a time zone. Each run posts its result or a question in the bot's thread, and starts within 60 seconds of its scheduled time.
- Weekly margins
- Mondays 7:00 AM, New York
- Inbox sweep
- Every 2 hours
- Renewal check
- Once, Nov 3 at 9:00 AM
A computer for every bot
Each bot gets its own cloud computer with a shell, a file system, a browser and a desktop. It starts when the bot needs it and sleeps when idle, keeping files and sign-ins. Watch the screen live and take control.
- Take control to sign in or solve a CAPTCHA, then hand it back
- Browse, upload and download the computer's files
Approvals
Before a bot sends, buys, deletes, posts or writes to an outside system, it posts an approval card. An approval nobody answers expires after 10 minutes and the action does not run.
Your choice of model
OpenAI, Anthropic, OpenRouter and any OpenAI-compatible endpoint. Each bot has a chosen model and an optional fallback used when the first one fails. Every call records tokens and cost; your workspace shows usage by bot and by day.
Coming later
Integrations. Connect remote MCP servers over HTTPS, including ones that sign in with OAuth. A connection belongs to you or to the workspace, and you choose which bots can use it. Requests to private network addresses are blocked. Planned
Subagents. A bot can start short-lived subagents for parallel subtasks and collect their results. The backend enforces the limits, not the model. Planned
Telegram, iMessage and SMS. Link a chat app or phone number with a one-time code and text any of your bots. Messages land in the same thread, and you can answer approvals from a text. Planned
Voice. Dictate messages, hear replies spoken aloud and hold a live voice call you can interrupt. Speech uses your workspace's own voice provider key, with OpenAI and ElevenLabs supported. Planned