Answer patient enquiries for a clinic by chat
An n8n and Gemini agent receives patient chat messages, keeps context, uses clinic info from Google Sheets and responds to enquiries.
A self-hosted company OS runs Claude Code and Codex agents per department, with memory, schedules, phone calls via Twilio, and document/video editing.
A self-hosted company OS runs Claude Code and Codex agents per department, with memory, schedules, phone calls via Twilio, and document/video editing.
OtoDock runs the real Claude Code and Codex as agents inside per-session kernel sandboxes, with network isolation on by default. Access is granted per folder or service through MCP tools. A dashboard streams each step and asks for approval on sensitive actions. Agents run on schedules or webhooks, keep editable memory, hold multi-agent meetings, and produce Word, Excel, PowerPoint and PDF files.
The README gives no outcome numbers. The author says large parts of OtoDock were built and shipped by agents running on it. Phone calls, which the summary mentions, are listed as shipping next, not yet available.
Install is a Docker compose file plus a Postgres password. Each user connects their own Claude or ChatGPT plan, API keys or local models. The license is fair source (FSL), which bars commercial competition.
Set up persistent agents for my [small company or project] with one agent each for [departments, e.g. sales, support, operations], each keeping notes between sessions and running a [daily or weekly] routine. Start by creating the structure and one useful scheduled task per department. Ask me before any agent sends a message, places a call, or edits a shared document.
An n8n and Gemini agent receives patient chat messages, keeps context, uses clinic info from Google Sheets and responds to enquiries.
An n8n workflow has AI classify web-form jobs by type, urgency and summary, create an Airtable record, reply instantly and flag uncertain cases.
Lindy agents summarized meeting notes, sent action items to teammates, suggested knowledge-base replies on support tickets, and handled follow-up emails and calendar updates.