Documentation
Everything you need to integrate AgentKavach into your AI agent stack.
Quickstart
Install the SDK and make your first budget-protected LLM call in under 2 minutes.
Providers
Full examples for OpenAI, Anthropic, Google, and Mistral with model lists and cross-provider comparison.
Budgets
Daily, monthly, and total budget types with in-memory enforcement and fail-open design.
Shared Budgets
Pool a single budget across multiple agents and providers with thread-safe enforcement.
Guardrails
Token limits, call count caps, runtime limits, and loop detection to keep agents in check.
Alerts
Slack, email, PagerDuty, and webhook alerts with configurable thresholds and templates.
YAML Configuration
Manage multiple agents, budgets, and alert channels from a single config file.
API Reference
REST endpoints for event ingestion, dashboard data, agent management, and billing.
Error Codes
Complete list of SDK exceptions and API error codes with troubleshooting guidance.
Pricing Models
Per-token pricing tables for every supported model across all providers.
Streaming
Budget-protected streaming with real-time token counting and GeneratorExit handling.
Security
TLS, JWT auth, HMAC signing, rate limiting, and best practices for production.
Changelog
Release history, breaking changes, and migration guides for every version.