trainingsites /
campus-ai-os
A folder-based AI chief of staff and team for solo course creators and coaches
- 53 stars
- 5 stars since 3 Oct
- Python
- Updated today
- Beginner friendly
- AI agents
Most AI chats start from zero, so you re-explain your audience, offers and voice each time. Campus AI OS writes that context into readable Markdown and JSON files in one folder, and every job starts from those files.
You talk to one AI, Dean, the chief of staff. Dean pulls the context a job needs, hands it to a department (Community, Education, Marketing or Sales), runs a playbook, and records what happened. Each run writes a results file, and an activity ledger logs who did what.
It is aimed at one-person businesses, not email and calendar assistance. There is no server, database, account or API key. It runs inside Claude Desktop, Cowork, Claude Code or Codex, and a /campus-doctor command checks the setup in plain language.
What it does
One chief of staff
Dean routes requests to the right department, runs the matching playbook and records the outcome. Nothing irreversible, such as publishing, sending or deleting, happens without your approval.
Memory in plain files
Identity, offers, goals, tasks, wiki and run records live in your folder. /wiki-ingest turns finished work into pages, and /wiki-query answers from them.
Skills, commands and playbooks
The README lists 43 skills, 36 commands, 2 playbooks (Weekly Reset, and One Recording to a Week of Content) and 2 niche packs.
Built-in health check
/campus-doctor reports problems in plain language, backs each line with an evidence command, and exits non-zero on failures. The repo ships 251 automated fixtures.
Works across several clients
Claude Desktop, Claude Code and Codex can share one campus. One configured client owns schedules and the shared ledger; the others write to their own logs.
What you could build
- Run a morning brief and weekly review built from your own business files.
- Turn one recording into a week of content with the repurpose playbook.
- Build a course structure and lesson plan with /build-course.
- Draft an email sequence or shape an offer around its outcome.
- Turn finished deliverables into a wiki you can query later.
Get started
In Claude Desktop or Cowork, download the .plugin file from the latest release and install it via Settings, Plugins, Install from file. Then connect an empty folder and say /campus-start to choose the quick start or full onboarding.
/plugin marketplace add trainingsites/campus-ai-os/plugin install campus-ai-os@campus-ai-os/campus-startCommands are copied from the project's README. Read it on GitHub for the full setup.
More in AI agents
openclaw
Self-hosted AI assistant that answers in your chat apps and runs on your own machine
hermes-agent
Self-hosted AI agent that keeps skills and memory, and chats via terminal or Telegram
TradingAgents
A team of LLM agents that debate and decide on stock trades, for research
paperclip
A Node.js server and React dashboard for running a team of AI agents like a company
autoresearch
Let an AI agent edit a small LLM training script overnight and keep what improves it
ruflo
Agent harness adding swarms, memory and plugins around Claude Code and Codex
OpenManus
Open-source general AI agent that runs tasks from your terminal with your own LLM key
multica
A shared board where you assign issues to AI coding agents like teammates
openhuman
Rust agent harness with a desktop app, terminal client and embeddable library
buzz
Self-hostable team workspace where people and AI agents share channels on a Nostr relay