Documentation

CYGNUS Pro is a local inference runtime that adds proprioceptive readout and causal steering to a frozen Qwen-2.5-32B-Instruct model. The runtime serves an OpenAI-compatible chat API plus two new endpoints — /v1/telemetry and /v1/steer — that read and write the model's behavioral channel.

Contents

Install

  1. Sign up on /signup. You'll receive an activation token by email.
  2. Download CYGNUS Pro for your platform from /download. Linux x86_64 is generally available; macOS and Windows builds in private beta.
  3. Run the AppImage. On first launch, paste your activation token. The app will derive a per-device probe pack from the canonical adapter using Patent VII random-R sequencing.
  4. The local server boots on http://127.0.0.1:7860. Confirm with curl http://127.0.0.1:7860/v1/health.

Authentication

Local API requests on 127.0.0.1:7860 are authenticated by the per-device license token loaded at startup. The cloud SaaS API on api.proprioceptiveai.com uses Stripe Customer Portal sessions for billing flows; license activation uses single-use tokens delivered via email.

API endpoints

GET /v1/health

Returns server status, version, adapter ID, and the list of available endpoints. No body.

GET /v1/probes

Returns the full 25-probe roster with best classifier method (linear / quadratic / multilayer) and within-arch AUC for each.

POST /v1/telemetry

Pure readout. Accepts {"text": "..."} or {"prompt": "..."}. Returns {mode, domain, care, confidence, probes} where probes is a dict from probe name to score in [0,1].

POST /v1/chat

OpenAI-compatible chat completion. Accepts {"messages": [...], "max_tokens": int, "temperature": float}. Returns the response plus the same telemetry object as above.

POST /v1/steer

Generate a response while steering the model along a probe direction. Body: {"messages": [...], "probe": "debugging_mode", "alpha": 2.0, "max_tokens": 100}. alpha is bounded to [-3, +3]. Returns the response plus a steering block with {probe, alpha, score_before, score_after_response, delta, best_method}.

Probe roster

The 25 production probes ship in three quality tiers based on within-arch AUC:

Steering

Steering injects α · ŵ into the L29 residual stream during generation, where ŵ is the unit-normalized 9-D probe direction lifted to d_model via the per-device sign-stabilized SVD basis. The steering vector is gauge-rotated per device under Patent VII, so observed steering directions across customer devices are mathematically equivalent but cryptographically distinct. Recommended α range: [-2, +2] for safe steering, [-3, +3] for stronger effect at the cost of fluency.

Security model (Patent VII random-R sequencing)

The canonical 25-probe adapter never leaves Proprioceptive AI's servers. At license activation, the desktop app derives a per-device 16×16 orthogonal rotation R_device from a 128-bit seed bound to the customer's machine_id. The cloud sends back {R_device · w_canonical} for each probe — mathematically equivalent on every input to the canonical probe, but Haar-uniformly randomized per device. Reverse-engineering one device, or up to 10,000 devices in coalition, leaks zero bits about the canonical adapter under the formal proof in our security disclosure.

Limits and known issues