sutra-dev is an open-source compiler for the Sutra programming language, designed for tensor operations on frozen-LLM embedding vectors. It supports vector-symbolic architectures, rotation binding, and integrates with PyTorch, providing developers with tools for advanced embedding manipulation and experimentation.
In the Infrastructure & Backend space, sutra-dev takes a focused approach. Enabling developers to perform advanced tensor operations on frozen-LLM embedding vectors using a dedicated programming language. sutra-dev is an open-source project aimed at machine learning developers. The project is open source (AGPL-3.0). The product ships for the web and the command line.
Emma Leonhart builds and maintains sutra-dev, and the product first shipped in 2026. The project is developed in the open on GitHub with 2.8k commits in the last 90 days. Across PulseGate's embedding index, sutra-dev has few near neighbours, marking it as relatively distinct. Among its 5 catalogued features are tensor ops, embedding vector support, and compiler.
Latest indexed changes and source events
sutralang.dev discovered by the PulseGate indexer
Other apps tracked under the same category.
