#771 · Primary category: AI Agents & Automation

harmonist

agent-framework agent-system ai-agents claude-code cursor-ide llm multi-agent-framework orchestration prompt-engineering python

Portable AI agent orchestration with mechanical protocol enforcement. 186 agents, zero runtime dependencies.

Project last updated:06/09/26

GitHub Stars

2.3K

Forks

207

Contributors

1

License

MIT

Why we included this project

Anyone who has watched an AI coding assistant promise to run a security review and then quietly skip it will recognize what Harmonist is trying to fix. It is a portable folder you drop into a project, and it turns your team's rules into IDE hooks that stop a code-changing turn from completing until the required reviewers actually ran. The enforcement lives in plain shell and Python scripts next to your code, not in a prompt the model can talk its way past, so a missing review or a tampered agent definition becomes a hard stop rather than a suggestion. With 193 focused agent roles and zero runtime dependencies beyond the standard library, it is a practical way for small teams to put real guardrails around agent-driven changes without adopting a heavy enterprise platform.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category