Story

Tessera is an activation-based protocol that lets trained ML models transfer knowledge to other models across architectures. Instead of dumping weight tensors, it encodes what a model has learnt — activations, feature representations, behavioural patterns — into self-describing tokens that a receiving model can decode into its own architecture.

The reference implementation (tessera-core) is a Python/PyTorch library. Current benchmarks show positive transfer across CNN, Transformer, and LSTM pairs. It runs on CPU and the demo finishes in under 60 seconds.

Happy to answer questions about the protocol design, the wire format, or the benchmark methodology.