Open source

The Unify agent harness is the open-source version of the runtime behind Unify Teammates. An agent carries out each request by writing and running Python, and can keep what worked for later requests.

In 2026 I led its ground-up redesign, with an agent mesh and a memory built for both memoization and generalisation. The Unify page tells that story and gives the results.

Before the harness was split out, I worked in Unify's full runtime, unifyai/unify, on how teammates read a company's files, the apps they generated, and their workflows.

Ivy was an open-source, source-to-source ML transpiler. Given a function, a model, or a whole library written in PyTorch, it produced working, readable TensorFlow or JAX source with the original control flow intact, so PyTorch code could be compiled with JAX or deployed through TensorFlow's tooling as source an engineer could still edit. Graph converters such as ONNX move only a model's computation graph.

I led it in two stages. At Unify I led the team on its graph tracer and transpiler, which traced a model into its computation graph and rebuilt that graph in another framework, and restructured an early prototype of source-to-source translation. At the Ivy spin-out the transpiler was rebuilt on that architecture, validated on Hugging Face models against the originals, and merged into Kornia. It is published on PyPI.

Kornia is a differentiable computer-vision library for PyTorch. With Ivy's source-to-source transpiler we worked through its functions and classes, fixing what the integration tests exposed in the transpiler until about 90% of them converted to TensorFlow, JAX, and NumPy. The integration, which added kornia.to_tensorflow(), kornia.to_jax(), and kornia.to_numpy(), was merged by Kornia's maintainers in October 2024 and shipped in Kornia 0.7.4.

In 2023 I co-mentored the Google Summer of Code 2023 project that set out to build Ivy into TensorLy, a Python library for tensor decomposition, tensor regression, and tensor algebra, so that TensorLy would be usable with any framework Ivy supported. TensorLy's users would switch backends through Ivy's backend handler instead of TensorLy's own. Part of the work landed in Ivy itself, as TensorLy-style tensor decompositions.