Six technical questions anchored to current code and published research. Every page identifies what is enforced, implemented, reference design, or unsolved before asking anyone to build with us.
Each note states a falsifiable problem, hard constraints, an evaluation plan, known status, and a first contribution. This is a research invitation, not a claim that each problem is already solved.
PCHP names identity, purpose, exact scope, validity, delivery, and receipt. The engineering question is whether those attributes can become machine-checkable invariants across a multi-tool agent plan, instead of natural-language promises around one.
Read the problem →ImplementedA useful private agent needs durable context, but sending an entire personal model to a backend defeats the premise. The problem is selective recall: enough relevant memory to help, no ambient plaintext collection, and an honest erase path.
Read the problem →ImplementedA streaming answer may look fluent long before it is trustworthy. The search harness carries a question through bounded conversation context, grounding sources, enabled connectors, synthesis, and SSE telemetry. The research gap is deciding whether that trace is sufficient for a person to inspect the result.
Read the problem →ImplementedTool descriptions tell a model what a tool does. They do not inherently say what the tool is allowed to do. The system separates read/search from action tools and enforces a consent-token gate for actions; the challenge is making that contract portable and hard to misdescribe.
Read the problem →Reference designThe local-first compute thesis treats placement as a human decision as well as a scheduler decision: stay local when latency or privacy makes that right; propose a temporary burst only when the task earns it. It is a design target, not a shipped control plane in this repository.
Read the problem →Open researchA private-agent company cannot honestly use conventional behavioral telemetry as its north-star instrument. The open problem is to estimate useful daily agents while treating the operator as an adversary and making individual behavior structurally difficult to observe.
Read the problem →Read the source, challenge the model, and make a small contribution that can survive a test harness.
One is a product of Hushh Technologies Corporation (brand: 🤫 “hussh”), an independent company. One runs on third-party silicon, systems, and cloud; platform names are used solely to describe where One software runs and imply no affiliation, endorsement, or sponsorship by those platforms. Our own go-to-market and bill-of-materials partner programs are real and actively in pursuit; we name a partner only once an agreement is executed.