The agent explains readings and answers questions about the console. Verdicts come from the rule set alone: no model output enters a decision, and the assistant cannot create, change or close an investigation. On the Ledger Garden screen (Desk) a walked path, with its full addresses, hashes and evidence, can be handed to the agent as one question that asks it to use only those facts.
Providers
| Provider | Runs | Cost to you | Key |
|---|---|---|---|
| Ollama | On this device | Free | Not needed |
| LM Studio | On this device | Free | Not needed |
| llama.cpp | On this device | Free | Not needed |
| Jan | On this device | Free | Not needed |
| vLLM | On this device | Free | Not needed |
| Claude (Anthropic) | Hosted | Provider pricing | Required |
| OpenAI | Hosted | Provider pricing | Required |
| Groq | Hosted | Free | Required |
| OpenRouter | Hosted | Provider pricing | Required |
| DeepSeek | Hosted | Provider pricing | Required |
| Mistral | Hosted | Provider pricing | Required |
A custom OpenAI-compatible endpoint can also be configured. If you configure a hosted AI provider, your prompts are processed by that provider under its terms.
Secrets never reach a model
A message containing a valid XRPL seed, recognised by its checksum, is refused before any request is made.
Oversight
- A policy submitted by one member must be activated by another; the server refuses self-activation.
- Policy exceptions are requested by one member and decided by another, and every decision is written to an append-only audit log.
- Investigations are opened, prioritised and closed by people. The AI assistant can be asked about a case but cannot create, change or close one.
- Every call to an AI model is recorded with digests and sizes, so what was sent and when can be shown without keeping a second copy of the text.
Generated from src/lib/agent/providers.ts · src/lib/agent/secrets.ts · src/lib/trust/boundary.json