See what an orchestra can produce

when your ideas

are the Partitura

Would a HUMAN team where the Tech Lead redirects a demand to the most fitting developer be 'multi-developer'? What about a Researcher that needs to summarize 10 articles, then asks for 10 other researchers to summarize one article each, then copies and pastes the 10 summaries together? Is this 'multi-researching'? If those scenarios wouldn't work for extremely competent and intelligent humans, why would it ever work for similarity algorithms?

Partitura is not a router to redirect your prompts to a selected agent... It's not an agent executing asynchronous tasks, or even one that creates clones of itself to execute parallel tasks and receive the results. It is very much like a team of individual agents. Each one with their own role and tools, working and collaborating under strict coordination, until you want them to stop.

I have to admit 'subagents' is a much closer dynamic than other 'multi-agent workflows' out there. But not exactly... in Partitura, a conductor writes no code, it doesn't even have tools to do so (Solo mode aside). Leadership is complex enough to handle, ensuring the team can work as a unit, planning the next steps and requirements while the others execute... as such, Frontend agents will waste no context with .go files, Debugger agents will waste no time implementing new features and Backend agents will know nothing about the appearance and style of the project. Each agent is an individual part of the whole.

No cloud servers storing a word about your projects, your data is not persisted anywhere in our system. We do offer Git compatibility (optional, and you can disable certain commands as well), but nothing outside your computer. Partitura won't ask for github credentials or access to your repositories either. However, it is EXTREMELLY important to note that what OpenAI, Anthropic, Google and any other providers do once your prompts reach their models is up to their own privacy policies (all available to check on the models you enable for your account, with warnings on the ones that openly disclose to use your data anonymously for model-training purposes).