I just open-sourced a fun side project of mine as I learned more about AI agent orchestrators.
Petri is an agent orchestration framework to grow your AI's context via Claude Code. Decomposes claims into DAGs of logical units and validates them bottom-up through a multi-agent adversarial review pipeline.
What results are a repository of curated information, citations, and URLs, organized by concepts, how they relate to each other, and the nuances of the claims. This is quite useful for AI agents to have pre-loaded context assets available for reference.
Petri includes both a CLI tool intended for AI agents and an interactive UI mode to help keep track of all active agents within Petri and to review the context, reasoning, and citations curated by the AI agents.
I just open-sourced a fun side project of mine as I learned more about AI agent orchestrators.
Petri is an agent orchestration framework to grow your AI's context via Claude Code. Decomposes claims into DAGs of logical units and validates them bottom-up through a multi-agent adversarial review pipeline.
What results are a repository of curated information, citations, and URLs, organized by concepts, how they relate to each other, and the nuances of the claims. This is quite useful for AI agents to have pre-loaded context assets available for reference.
Petri includes both a CLI tool intended for AI agents and an interactive UI mode to help keep track of all active agents within Petri and to review the context, reasoning, and citations curated by the AI agents.
You can learn more about how it works here: https://github.com/onthemarkdata/petri/blob/main/ARCHITECTUR...