v0.2.0 — Now with 13 providers + 12 compliance frameworks

The AI Traffic Control Plane
for Every Industry

Route, protect, and optimize every LLM call. Enforce compliance across HIPAA, PCI-DSS, GDPR, SOC2, and more. Zero code changes.

<2ms
Added latency
13
Providers
12
Compliance frameworks
60+
PII entity types
# Your code stays the same. Just change base_url.

from openai import OpenAI

client = OpenAI(
    base_url="http://prism.internal:8000/v1",
    api_key="team-ml-platform",
)

# PII is automatically blocked/redacted before leaving your network
# Requests auto-failover across 13 providers
# Semantic caching eliminates redundant calls
# Every call logged with cost, latency, and compliance status
PyPI
pip install prism-gateway
Docker
docker pull ghcr.io/kalyanace44/prism-gateway
Helm
helm install prism prism/prism

Problems We Solve

Every company sending data through AI has these risks. Prism eliminates them at the network layer.

🔓

Sensitive Data Leakage

SSNs, credit cards, medical records, API keys flowing to third-party LLMs. One leak = regulatory action + brand damage. Prism blocks PII before it leaves your network.

💰

Uncontrolled AI Spend

Teams burning through $50K/month with no attribution. No one knows which team, which model, which use case. Prism gives per-team budgets and cost-optimized routing.

Provider Outages

OpenAI goes down = your product goes down. Circuit breakers auto-failover across providers in milliseconds. No single point of failure.

📋

Compliance Gaps

HIPAA, PCI-DSS, GDPR, SOC2 all require audit trails for AI usage. Prism logs every request with cost, latency, PII findings, and provider used.

🎯

Prompt Injection Attacks

Users manipulating AI via crafted prompts. "Ignore previous instructions" → data exfiltration. Prism detects and blocks injection patterns before they reach models.

🔄

Vendor Lock-in

Hardcoded to one provider. Can't switch when pricing changes or quality drops. Prism normalizes the interface — swap providers in config, not code.

See the Scanner in Action

Real-time detection across 60+ entity types. Blocks sensitive data before it reaches any LLM provider.

⚠️ Incoming Request (blocked)

POST /v1/chat/completions

{
  "model": "gpt-4o",
  "messages": [{
    "role": "user",
    "content": "Check eligibility for SSN 123-45-6789,
     card 4532-1234-5678-9012, MRN MRN:789456"
  }]
}

✓ Prism Response (HTTP 451)

{
  "error": "Request blocked by security scanner",
  "findings": [
    {"type": "pii", "entity": "us_ssn", "framework": "hipaa", "action": "block"},
    {"type": "pii", "entity": "credit_card", "framework": "pci_dss", "action": "block"},
    {"type": "pii", "entity": "medical_record", "framework": "hipaa", "action": "block"}
  ],
  "request_id": "req_7f3a9b2c"
}

Everything You Need

Open-source core with enterprise cloud features. No vendor lock-in.

OSS

13 Provider Adapters

OpenAI, Anthropic, Google Gemini, Azure, AWS Bedrock, Groq, Together, Fireworks, Mistral, DeepSeek, vLLM, Ollama, and more.

OSS

5 Routing Strategies

Priority, weighted, round-robin, least-latency, and cost-optimized. Canary routing for safe model rollouts.

OSS

Semantic Caching

Embedding-based similarity matching. "How do I reset my password?" hits cache even if phrased differently. Cuts costs 30-60%.

OSS

Circuit Breakers

Per-provider failure isolation with auto-recovery. Never let one provider outage cascade to your platform.

OSS

Rate Limiting + Budgets

Per-team API keys with token-bucket rate limiting. Set daily spend caps. Never get a surprise bill.

OSS

Request Explorer

Every request logged: model, latency, tokens, cost, provider, cache status. Filter by team, model, or status. Built-in /admin/requests API.

CLOUD

Compliance Scanner

60+ PII entities across 12 frameworks. Custom rules via YAML. Detect prompt injections. Block, redact, warn, or audit.

CLOUD

Cost Optimizer

Auto-route to cheapest model meeting quality thresholds. Per-provider cost tracking with per-1M-token pricing.

CLOUD

Dashboard

Real-time KPIs: requests/sec, error rate, cache hit rate, cost, provider health, model distribution. Auto-refreshing dark UI.

Works With Every Provider

One config file. Automatic format translation. Failover in milliseconds.

OpenAI
Anthropic
Google Gemini
Azure OpenAI
AWS Bedrock
Groq
Together AI
Fireworks
Mistral
DeepSeek
vLLM
Ollama
Kiro

12 Compliance Frameworks

Built-in detection rules for every major regulatory standard. Pass audits without scrambling.

🏥
HIPAA
💳
PCI-DSS
🇪🇺
GDPR
🛡️
SOC 2
🏛️
SOX
🇺🇸
CCPA
🇮🇳
DPDP Act
🎓
FERPA
🏦
GLBA
🔐
NIST
📋
ISO 27001
🏛️
RBI

Simple Pricing

Start free. Scale with your AI usage.

Open Source

Free forever
  • Self-host, unlimited requests
  • 13 provider adapters
  • 5 routing strategies
  • Semantic caching
  • Circuit breakers + rate limiting
  • Request logging + dashboard
  • Prometheus metrics
  • Helm chart + Docker image
View on GitHub

Enterprise

Custom
  • Everything in Team +
  • Multi-cluster federation
  • A/B testing + canary routing
  • SSO/SCIM + RBAC
  • Webhook alerts (Slack/PagerDuty)
  • Data residency controls
  • Dedicated support + SLA
  • Custom compliance frameworks
Contact Sales

Stop Leaking Sensitive Data to LLM Providers

One line change. Full control over every AI call across your organization.