I Gave My AI Agents an Org Chart

Manoj Kumar Kagitha, a senior cloud engineer, has released Botropolis, an MIT-licensed open-source Python framework that organizes 20 specialist AI agents into ten departments under a CEO orchestrator named Manoj. Each agent is defined by a YAML spec listing its name, title, specialty, tools and example tasks, and the system runs with no API keys against an offline stub. File and shell tools are sandboxed to a workspace directory with timeouts and a denylist, while health and legal agents carry explicit disclaimers.

Most agent frameworks hand you a pile of scripts and wish you luck. You wire up three agents, write the orchestration glue yourself, and six weeks later you have a system nobody can explain. I kept running into this, so I built something with a different shape: a company. It is called Botropolis. Twenty specialist agents across ten departments, one CEO orchestrator, and a training pipeline so each agent can eventually get its own fine-tuned model. It is open source, MIT licensed, and it runs with no API keys. Companies figured out coordination centuries ago. When work gets complex, you do not throw twenty generalists into a chat room. You create departments, give people job titles, and let a manager break big requests into pieces. Botropolis is that idea in Python. You ask Manoj, the CEO, for something. He looks at the request, decides which departments need to be involved, and routes the work. Research goes to Scout, code goes to Coder, the numbers go to Analyst. Each agent has a YAML spec: name, title, specialty, tools it may call, example tasks. Anyone reading the repo can see who does what, the way an org chart tells you who owns what. The roster covers ten departments: research, health, finance, code, data, legal, marketing, ops, security, and support. Some highlights: It runs with zero API keys against an offline stub that labels its output as stub output. Clone it, run python examples/demo.py , and watch the whole company work before spending anything. The safety model is pragmatic, not paranoid. File and shell tools are sandboxed to a workspace directory with timeouts and a denylist for destructive patterns. Agents draft emails; humans send them. Health and legal agents carry explicit disclaimers in their prompts. git clone https://github.com/kagithamanoj/botropolis.git cd botropolis pip install -e ". dev " python examples/demo.py Or skip the clone and talk to the CEO directly: python from botropolis.core.orchestrator import CEO report = CEO .handle "Research vector databases and compare pricing" print report.summary The org chart grows by pull request. If you have ever wanted an agent with a job title, come add a department. Botropolis is built and maintained by Manoj Kumar Kagitha, a Senior Cloud Engineer working on production cloud infrastructure. Nine papers, seven books, and now one company of bots.