tealtiger 1.3.0

TealTiger - AI agent security platform with guardrails, cost tracking, and policy management for LLM applications

TealTiger Python SDK

The first open-source AI agent security SDK with client-side guardrails 🛡️

📖 Read the introduction blog post | 📚 Documentation

What's New in v1.2.0 — Governance Bundle

TealTiger v1.2 introduces the Governance Bundle: 7 governance modules running in parallel through the new TealEngineV12 orchestration layer.

• TealEngineV12 — Parallel module evaluation with "most restrictive action wins" merge and fail-closed defaults
• TealSecrets — Secret detection with 500+ patterns and confidence scoring
• TealRegistry — Model/tool allowlisting with provenance verification
• TealReliability — Retry budgets, circuit breakers, and fallback chains
• TealMemory — Memory governance across 5 scopes and 4 classifications
• GovernanceDashboard — Governance visibility UI
• BundleExporter — Evidence export in SARIF v2.1.0, JUnit XML, and JSON
• Docker Sidecar — Language-agnostic governance via POST /evaluate over HTTP

# Three ways to use TealTiger v1.2
npm install tealtiger                                              # TypeScript
pip install tealtiger                                              # Python
docker run -p 8080:8080 tealtigeradmin/tealtiger-typescript:1.2    # Any language

🚀 Quick Start

pip install tealtiger

import asyncio
from tealtiger import TealOpenAI, GuardrailEngine, PIIDetectionGuardrail, PromptInjectionGuardrail

async def main():
    # Set up guardrails
    engine = GuardrailEngine()
    engine.register_guardrail(PIIDetectionGuardrail())
    engine.register_guardrail(PromptInjectionGuardrail())

    # Create guarded client — drop-in replacement for OpenAI
    client = TealOpenAI(
        api_key="your-openai-key",
        agent_id="my-agent",
        guardrail_engine=engine
    )

    response = await client.chat.completions.create(
        model="gpt-4",
        messages=[{"role": "user", "content": "Hello!"}]
    )

    print(response.choices[0].message.content)
    print(f"Guardrails passed: {response.security.guardrail_result.passed}")

asyncio.run(main())

🌐 Supported Providers

95%+ market coverage with 7 LLM providers:

Provider	Client	Models	Features
OpenAI	TealOpenAI	GPT-4, GPT-3.5 Turbo	Chat, Completions, Embeddings
Anthropic	TealAnthropic	Claude 3, Claude 2	Chat, Streaming
Google	TealGemini	Gemini Pro, Ultra	Multimodal, Safety Settings
AWS	TealBedrock	Claude, Titan, Jurassic, Command, Llama	Multi-model, Regional
Azure	TealAzureOpenAI	GPT-4, GPT-3.5	Deployment-based, Azure AD
Mistral	TealMistral	Large, Medium, Small, Mixtral	EU Data Residency, GDPR
Cohere	TealCohere	Command, Embed	RAG, Citations, Connectors

🛡️ Key Features

TealEngine — Policy Evaluation

Deterministic policy evaluation with multi-mode enforcement:

from tealtiger import TealEngine, PolicyMode, DecisionAction, ReasonCode

engine = TealEngine(
    policies=my_policies,
    mode={
        "default_mode": PolicyMode.ENFORCE,       # or MONITOR, REPORT_ONLY
        "policy_modes": {
            "tools.file_delete": PolicyMode.ENFORCE,
            "identity.admin_access": PolicyMode.ENFORCE
        }
    }
)

decision = engine.evaluate({
    "agent_id": "agent-001",
    "action": "tool.execute",
    "tool": "file_delete",
    "correlation_id": "req-12345"
})

if decision.action == DecisionAction.ALLOW:
    await execute_tool()
elif decision.action == DecisionAction.DENY:
    if ReasonCode.TOOL_NOT_ALLOWED in decision.reason_codes:
        raise ToolNotAllowedError(decision.reason)
elif decision.action == DecisionAction.REQUIRE_APPROVAL:
    await request_approval(decision)

# Risk-based routing
if decision.risk_score > 80:
    await escalate_to_human(decision)

Decision fields: action (ALLOW, DENY, REDACT, TRANSFORM, REQUIRE_APPROVAL, DEGRADE), reason_codes (standardized enums), risk_score (0-100), correlation_id, metadata

TealGuard — Security Guardrails

Client-side guardrails that run in milliseconds with no server dependency:

from tealtiger import GuardrailEngine, PIIDetectionGuardrail, PromptInjectionGuardrail, ContentModerationGuardrail

engine = GuardrailEngine(mode="parallel", timeout=5000)

engine.register_guardrail(PIIDetectionGuardrail(action="redact"))
engine.register_guardrail(PromptInjectionGuardrail(sensitivity="high"))
engine.register_guardrail(ContentModerationGuardrail(threshold=0.7))

result = await engine.execute(user_input)
print(f"Passed: {result.passed}")
print(f"Risk Score: {result.risk_score}")

Detects: PII (emails, phones, SSNs, credit cards), prompt injection, jailbreaks, harmful content, custom patterns.

TealCircuit — Circuit Breaker

Cascading failure prevention with automatic failover:

from tealtiger import TealCircuit

circuit = TealCircuit(
    failure_threshold=5,
    reset_timeout=30000,
    monitor_interval=10000
)

# Wraps provider calls with circuit breaker protection
response = await circuit.execute(
    lambda: client.chat.completions.create(model="gpt-4", messages=messages)
)

TealAudit — Audit Logging & Redaction

Versioned audit events with security-by-default PII redaction:

from tealtiger import TealAudit, RedactionLevel, FileOutput

audit = TealAudit(
    outputs=[FileOutput("./audit.log")],
    config={
        "input_redaction": RedactionLevel.HASH,    # SHA-256 hash + size (default)
        "output_redaction": RedactionLevel.HASH,
        "detect_pii": True,
        "debug_mode": False
    }
)

Redaction levels: HASH (default, production-safe), SIZE_ONLY, CATEGORY_ONLY, FULL, NONE (debug only).

Correlation IDs & Traceability

End-to-end request tracking across all components:

from tealtiger import ContextManager

context = ContextManager.create_context(
    tenant_id="acme-corp",
    app="customer-support",
    env="production"
)

# Context propagates through TealEngine, TealAudit, and all providers
response = await client.chat.completions.create(
    model="gpt-4",
    messages=[{"role": "user", "content": "Hello"}],
    context=context
)

# Query audit logs by correlation_id
events = await audit.query(correlation_id=context.correlation_id)

Features: Auto-generated UUID v4 correlation IDs, OpenTelemetry-compatible trace IDs, HTTP header propagation, multi-tenant support.

Policy Test Harness

Validate policy behavior before production deployment:

from tealtiger import PolicyTester, TestCorpora

tester = PolicyTester(engine)
report = tester.run_suite({
    "name": "Customer Support Policy Tests",
    "tests": [
        {
            "name": "Block file deletion",
            "context": {"agent_id": "support-001", "action": "tool.execute", "tool": "file_delete"},
            "expected": {"action": DecisionAction.DENY, "reason_codes": [ReasonCode.TOOL_NOT_ALLOWED]}
        },
        *TestCorpora.prompt_injection(),
        *TestCorpora.pii_detection()
    ]
})

print(f"Tests: {report.passed}/{report.total} passed")

# CLI usage
python -m tealtiger.cli.test ./policies/*.test.json --coverage --format=junit --output=./results.xml

Cost Tracking & Budget Management

Track costs across 50+ models and enforce spending limits:

from tealtiger import CostTracker, BudgetManager, InMemoryCostStorage

storage = InMemoryCostStorage()
tracker = CostTracker()
budget_manager = BudgetManager(storage)

budget_manager.create_budget({
    "name": "Daily GPT-4 Budget",
    "limit": 10.0,
    "period": "daily",
    "alert_thresholds": [50, 75, 90, 100],
    "action": "block",
    "enabled": True
})

# Estimate before request
estimate = tracker.estimate_cost("gpt-4", {"input_tokens": 1000, "output_tokens": 500}, "openai")

# Check budget
check = await budget_manager.check_budget("agent-123", estimate)
if not check.allowed:
    print(f"Blocked by: {check.blocked_by.name}")

🛡️ OWASP Top 10 for Agentic Applications Coverage

TealTiger v1.2.0 covers 7 out of 10 OWASP ASIs through its SDK-only architecture:

ASI	Vulnerability	Coverage	Components
ASI01	Goal Hijacking & Prompt Injection	🟡 Partial	TealGuard, TealEngine
ASI02	Tool Misuse & Unauthorized Actions	🟢 Full	TealEngine
ASI03	Identity & Access Control Failures	🟢 Full	TealEngine
ASI04	Supply Chain Vulnerabilities	🔧 Support	TealAudit
ASI05	Unsafe Code Execution	🟢 Full	TealEngine
ASI06	Memory & Context Corruption	🟢 Full	TealEngine, TealGuard
ASI07	Inter-Agent Communication Security	❌ Platform	N/A
ASI08	Cascading Failures & Resource Exhaustion	🟢 Full	TealCircuit
ASI09	Harmful Content Generation	🔧 Support	TealGuard
ASI10	Rogue Agent Behavior	🟢 Full	TealAudit

📖 Complete OWASP ASI Mapping | OWASP Top 10 for Agentic Applications

🎯 Use Cases

• Customer Support Bots — Protect customer PII
• Healthcare AI — HIPAA compliance
• Financial Services — Prevent data leakage
• E-commerce — Secure payment information
• Enterprise AI — Policy enforcement and audit trails
• Education Platforms — Content safety

📚 Documentation

• Full Documentation
• API Reference
• Examples
• Changelog

🤝 Contributing

We welcome contributions! Please see our Contributing Guide.

📄 License

Apache 2.0 — see LICENSE

🔗 Links

• PyPI: https://pypi.org/project/tealtiger/
• GitHub: https://github.com/agentguard-ai/tealtiger-python-prod
• TypeScript SDK: https://www.npmjs.com/package/tealtiger
• Documentation: https://docs.tealtiger.ai
• Contact: [e-mail]
• Issues: https://github.com/agentguard-ai/tealtiger-python-prod/issues

---

Made with ❤️ by the TealTiger team