plato-neural-kernel is an open-source CLI tool that converts execution traces into training pairs for neural Plato models. It streamlines the data preparation process for AI researchers and developers working on neural model training.
plato-neural-kernel is a LLM eval & observability product. It focuses on automating the conversion of execution traces into training pairs for neural model development. It is built as an open-source project for AI researchers and developers. plato-neural-kernel is open source under the MIT license. It runs on the web and the command line, and it can be self-hosted.
Behind plato-neural-kernel is SuperInstance, and the product first shipped in 2026. Development happens publicly on GitHub with 3 commits in the last 90 days. Key capabilities include trace conversion, training data generation, and CLI tool.
Latest indexed changes and source events
Other apps tracked under the same category.
