TorkOpen Source AI Governance

The Universal Governance Layer for AI Agents

Enforce policies, redact PII, and audit compliance across |

Start Free Trial View on GitHub
$ pip install tork-governance

# In 3 lines of code:
from tork import PolicyEngine
engine = PolicyEngine.from_yaml("policy.yaml")
result = engine.evaluate(agent_output)

Works with 12+ AI frameworks

LangChainCrewAIAutoGenOpenAIMCPAnthropicLlamaIndexFastAPIHugging FaceMistralSemantic KernelAWS Bedrock
LangChainCrewAIAutoGenOpenAIMCPAnthropicLlamaIndexFastAPIHugging FaceMistralSemantic KernelAWS Bedrock
LangChainCrewAIAutoGenOpenAIMCPAnthropicLlamaIndexFastAPIHugging FaceMistralSemantic KernelAWS Bedrock
12+
Frameworks Supported
<5ms
Evaluation Latency
100%
Local Processing
MIT
Open Source License
Features

Everything You Need for AI Governance

Enterprise-grade compliance without enterprise complexity

Policy Enforcement

Define rules in YAML, enforce everywhere. Block, warn, or allow based on content.

Learn more →

PII Redaction

Automatically detect and redact 50+ PII types. Emails, phones, SSNs, credit cards.

Learn more →

Compliance Receipts

HMAC-signed, tamper-evident audit trails. Prove compliance with cryptographic certainty.

Learn more →

Listen Mode

Deploy in observation mode first. Tork learns your traffic patterns automatically.

Learn more →

Human-in-Loop

Route sensitive decisions to humans. Configurable escalation paths.

Learn more →

Framework Agnostic

Works with LangChain, CrewAI, AutoGen, or raw API calls.

Learn more →

Tork significantly reduces AI safety risks through multiple detection layers. No AI safety solution guarantees 100% protection. We recommend using Tork as part of a defense-in-depth strategy. See our Terms of Service for details.

How It Works

Three Steps to Governed AI

01

Define Policies

Write human-readable YAML policies.

policies:
  - name: pii-protection
    action: REDACT
    patterns: [email, phone]
02

Wrap Your Calls

Add Tork to your AI pipeline.

from tork import PolicyEngine
engine = PolicyEngine("policy.yaml")
result = engine.evaluate(output)
03

Monitor & Audit

Get dashboards and receipts.

# Every evaluation creates
# a signed receipt:
{
  "decision": "ALLOW",
  "hmac": "a3f2c1..."
}
Pricing

Start Free, Scale with Confidence

Open source core. Premium features for teams.

MonthlyAnnualSave 20%
OPEN SOURCE
Free
Forever, for everyone
  • Policy enforcement
  • PII redaction (10+ types)
  • Local audit logs
  • Community support
  • MIT licensed
Get Started
STARTER
$39/mo
Billed $468/year
  • Everything in Free
  • 50+ PII types
  • Cloud receipt storage
  • Email support
  • API access
POPULAR
PROFESSIONAL
$159/mo
Billed $1,908/year
  • Everything in Starter
  • Dashboard & analytics
  • SSO / SAML
  • Priority support
  • Custom policies
  • Webhooks
ENTERPRISE
Custom
For large organizations
  • Everything in Pro
  • Unlimited scale
  • On-prem deployment
  • Custom integrations
  • SLA guarantee
  • Dedicated support
Contact Sales

Ready to Govern Your AI?

Join developers building trustworthy AI systems with Tork.

Start Free Trial Star on GitHub