← All work

Local AI / Distributed Systems / 2026

Sylph

Local intelligence. Shared learning.

I am building a Rust runtime for local inference and exploring peer-to-peer exchange of model adapters.

RustLocal inferenceLoRAPeer-to-peer

Research — In development

CONTRIBUTION & EVIDENCE
Run the workflow

Inspect an arriving adapter.

Inspect the compatibility and integrity gates around a received model-adapter update. Click a step, connection, or trace to inspect it.

Execution trace / Click to inspect

Start the walkthrough, or inspect any step before running it.

Simplified from the project architecture. Runs locally; no live models, credentials, or external services.

Sylph / Inspector

Workflow overview

Offer

A peer offers metadata describing a model-adapter delta.

Why it matters

Compatibility and integrity are separate gates. Passing them does not establish that an adapter is beneficial or safe in every composition; evaluation continues beyond these checks.

Synthetic payloads explain the boundaries. They are illustrative examples, not project API schemas or live production traces.

The engineering

Inside
the decisions.

Connect local inference and shared learning through explicit trust boundaries.

Local AI needs more than a model loader. It needs a consistent runtime, a way to learn from useful work, and a trust boundary around knowledge received from other machines.

01

The design decision

Separate the inference backend, adapter exchange, and validation layers. Check adapter compatibility and payload integrity before accepting a received update.

02

The trade-off

Decentralized learning adds compatibility, privacy, and trust problems to inference. Module-level checks are useful evidence; broad model support and the complete learning loop still need end-to-end evaluation.

03

Separating the model backend

Developed a backend-agnostic inference contract and runtime infrastructure in Rust.

04

Exchanging compatible adapters

Explored task-driven learning and model-adapter workflows, including compatibility checks for exchanging adapter updates.

05

Checking received payloads

Implemented peer-to-peer delta validation around base-model identity, adapter structure, payload integrity, and bounded decompression.

06

Testing composition and deployment

Developed composition checks and adversarial tests for received adapters, with deployment tooling spanning local environments and Kubernetes/Helm.

Read the system flow

Sylph · Public explanation of the implementation boundaries.

  1. Local runtimeA backend contract separates inference from the surrounding system.
  2. Candidate adapterTask-driven learning explores deriving an adapter update from useful work.
  3. Exchange checksCheck base-model identity, structure, payload integrity, and decompression bounds.
  4. Evaluation boundaryCompatibility is a prerequisite; useful and safe model behavior needs separate evaluation.

Implemented and tested at module level

Runtime contracts, adapter compatibility, payload validation, composition checks, and adversarial tests exist in the private implementation. Local and Kubernetes/Helm tooling support deployment experiments.

End-to-end validation remains open

The complete learning loop and broad model support remain under evaluation. The browser exhibit runs SHA-256 and base-model checks on sample data; it does not execute the Rust runtime or evaluate model quality.

Trust boundary: peers and payloads

Received adapters cross an untrusted peer boundary. Identity, structure, digest verification, and bounded decompression address malformed or incompatible input. A matching digest establishes byte integrity, not a trustworthy sender.

Trust boundary: behavior and recovery

Poisoning, private-data leakage, unsafe composition, and rollback require separate evaluation. No general safety, privacy, or rollback guarantee is made for the current implementation.

Research — In development

Inspect
the work.

An independent project in development, with a public project overview and a private implementation. Current work explores inference, learning, adapter exchange, and validation. Broad model coverage and end-to-end safety remain goals requiring continued evaluation.

Next project: Memory-Arc ↗

Source material

Public project overview
Public project overview. The implementation is private and remains in development.

Opening the project index…

Browse all work ↗

Interactive exhibit