Files
ppq-private-mode-startos/instructions.md
T
mattius459andClaude Fable 5 b6b2589c55 PPQ Private Mode StartOS package
Wraps the ppq-private-mode-proxy (git submodule, built from its own
Dockerfile) as a StartOS 0.4.0 service:
- Critical first-run task + masked action to set the PPQ.AI API key
- OpenAI-/Anthropic-compatible API interface on port 8787
- Health check reflects enclave attestation (proxy binds only after
  attestation succeeds)
- x86_64 + aarch64, config backed up via the main volume

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-27 22:27:38 +02:00

1.8 KiB

PPQ Private Mode

Documentation

Getting set up

  1. When the service is installed, you will be prompted to run Configure PPQ API Key. Paste an API key from ppq.ai (create one under Settings → API Keys and fund the account — usage is billed per query to this key).
  2. The service starts and performs a cryptographic attestation of the remote enclave. The health check reports ready once attestation is verified — usually within a few seconds.
  3. Copy the OpenAI-Compatible API address from the service's interface panel. That is the URL you point your AI clients at.

Using the proxy

Point any OpenAI-compatible client at the interface address:

POST <api-address>/v1/chat/completions
{"model": "private/glm-5-2", "messages": [{"role": "user", "content": "Hello"}]}

Anthropic-SDK clients (including Claude Code) can use the native endpoint at <api-address>/v1/messages. For Claude Code, set:

export ANTHROPIC_BASE_URL="<api-address>"
export ANTHROPIC_MODEL="private/glm-5-2"

GET <api-address>/v1/models lists the available private models. Every request is encrypted on your server before it leaves and is only decrypted inside the attested enclave — neither PPQ.AI nor the model host can read your queries.

Requests are billed to your saved API key by default. To bill a different PPQ.AI key per request, pass it as an Authorization: Bearer header.

If you need to change the key or turn on verbose logging later, run Configure PPQ API Key again from the service's Actions.