Quickstart

Vibe-to-Production
in 60 seconds.

Modern high-fidelity docs prioritize context over feature-lists. Start by shielding your local VPC, pointing your agent to the Spendplane proxy, and watching the infrared scanner redact PII in real-time.

01

Tunnel Setup

Run `npx spendplane tunnel` to bridge your local GPU to the global proxy.

02

Set Handshake

Paste your VPC key into Cursor or the V1 SDK to authorize the 'Shadow Plane'.

03

Execute Hot-Lane

Ship code with 100% data sovereignty. Check the Vibe Debugger below for live logic.

How do I route v0 traffic to Llama-3?

Living API Reference

Don't just read documentation. **Test it**. Paste a raw LLM prompt below and watch our agent-fit logic scrub sensitive data before it ever hits the cloud.

Vibe Debugger

Infrared PII Scanner v2.6

Live Logic Active
Low Latency
Hey, my email is [PRIVATE_EMAIL] and my development key is sk-[SECURE_PHONE]abcdef. Please check the logs at [TUNNEL_IP].

Spending Shield Active: Your keys and PII are stripped before they leave your local VPC. LLMs never see your raw identity.

The governance tunnel

Control exactly what leaves your network.

Spendplane captures the request, applies policy, picks the cheapest viable lane, and shows the live decision instead of hiding it behind the agent.

The Scrubbing Layer

Before any token hits an LLM, your request passes through Spendplane's proxy. We automatically scan for sensitive PII using specialized models, strip redundant data, and apply budget guardrails.

  • Automatic PII redaction
  • Context compression
  • Budget enforcement
Original payload: draft reply for John Doe (jdoe@acme.com)...
Local Fast Lane (Selected)
Free
Budget Cloud
Optimal
Premium Assist
$0.04/req

Intelligent Routing

Not every prompt needs GPT-4. Spendplane dynamically routes your payload to the cheapest capable model based on task complexity, slashing your cloud bill without sacrificing quality.

  • Model cascading capabilities
  • Cost-threshold fallbacks
  • Latency-aware selection

Trace, Restore & Deliver

Watch the full lifecycle in real-time. Once the LLM responds with scrubbed tokens, Spendplane securely re-maps them to their original values and delivers a complete, private response to your app — zero PII ever leaked.

  • Full payload introspection
  • Secure PII re-insertion on return
  • Cost attribution per request
  • Zero-leak delivery guarantee
Spendplane terminal

_

Spendplane Recipes

Developers in 2026 love "copy-pasteable" success. Grab these pre-validated configs to kickstart your production stack.

Cost Optimization

The $5/mo Bolt.new Portfolio

Routing all non-critical architectural tasks to Llama-3.1 via local proxy while keeping frontend-hot-reloading in the cloud.

.env
SPENDPLANE_ROUTING=hybrid
LOCAL_GPU_PRIORITY=high
MAX_CLOUD_SPEND=5.00
config.json
{ "models": ["llama-3.1-8b"], "provider": "spendplane-local" }
Governance

The HIPAA Healthcare Bot

PII Scrubbing + 100% Data Retention at Source. Ensure zero patient data ever hits third-party model providers.

.env
SPENDPLANE_ENFORCER=strict
PII_REDACTION=enabled
RETENTION_POLICY=source_only
config.json
{ "security": { "pii_scanner": "deep", "vault_key": "VPC_ROOT" } }

Engineering Trust

Spendplane is built for the most sensitive workloads in 2026. From HIPAA-compliant healthcare bots to sovereign defense-layer LLMs, we guarantee that your data stays in your VPC.

Compliance Documentation

Contact us for current materials.

HIPAA Ready

BAA available for Enterprises.

Sovereignty

Keys stay in your VPC, always.

GDPR Proof

Data never leaves the EU tunnel.

Security Review Request
Contact Enterprise Security