Open software portfolio

Choose a project by the problem it helps you solve.

Our projects span local data and memory, observable training, controlled transformer research, and CPU inference. Each has its own maturity, evidence, and next steps.

01 / Local data and agent memory

Hyphae

A local data engine and shared memory for coding agents, with retrieval and verifiable records.

Stable 3.0.0

Explore this softwareRust / Apache-2.0

02 / Training instrumentation research

Hytorch

A research prototype that records internal training writes, making them auditable and replayable.

Research prototype / preprint 1.1

Explore this softwareRust + Python / Apache-2.0

03 / Controlled transformer research

Hyphae Transformer

Controlled transformer experiments and bounded controllers over frozen models.

Public alpha 0.2.0

Explore this softwarePython + PyTorch / MIT

04 / Exact ternary CPU inference

Hyphae BitNet

CPU inference for supported ternary models, with exact integer contracts and explicit memory budgets.

Runtime 0.3.2 / release tag v0.3.3

Explore this softwareC/C++ + Python / Apache-2.0

Ecosystem integration

Hyphae Memory for Omarchy

Hyphae Memory brings project memory to the Omarchy desktop through an independently managed local service.

Client 0.2.0 / separate service required

Explore this software

Shared approach

A public record that connects the work.

Hyphae provides durable data and memory. Hytorch uses that foundation to record training writes. Transformer studies architecture and control under fixed protocols. BitNet makes numerical and hardware contracts explicit.

Useful systems, open methods, and enough evidence for someone else to assess the result.

Collaboration

Find a practical starting point.

We can discuss a research question, a scoped pilot, an independent reproduction, or sponsorship of a defined piece of open work.

Discuss a collaboration