Skip to main content

​
Key Features

Cost Analytics

Real‑time insight into token usage and spend across models, agents, and templates

Policy Engine

Set budgets and alerts, enforce limits, and prevent runaway costs

Prompt Management

Author, version, validate, and render templates with reusable parts

Performance Monitoring

Track latency and errors; explore timelines for chat and tool executions

​
Quick Example

Render a template with the Python SDK: 
import asyncio
from dotenv import load_dotenv
from dakora_client import Dakora

# Load environment variables from .env file
load_dotenv()


async def main():
    # uses env vars: DAKORA_API_KEY and DAKORA_BASE_URL
    # initialize Dakora client
    dakora = Dakora()

    # Render a Dakora template and run it through the agent (auto-tracked)
    faq_template = await dakora.prompts.render(
        "faq_responder",
        {
            "question": "What is Dakora?",
            "knowledge_base": "**Dakora** is an open‑source AI observability and prompt management platform that delivers real‑time cost analytics, policy controls, and a hosted studio to help teams make every token count. Learn more at https://dakora.io.",
            "tone": "helpful",
            "include_sources": True,
        },
    )

    print("Rendered template:\n\n", faq_template.text)


asyncio.run(main())

​
Works With Your Stack

  • Microsoft Agent Framework
  • Soon: OpenAI Agents, LangChain and many more

​
Get Started

Live Playground

Try Dakora in your browser without installing anything

Quick Start

Get up and running in minutes

​
Dig Deeper

Core Concepts

Learn about templates, vault, and inputs

Features

Explore logging, integrations, and the playground

REST API

Explore project‑scoped endpoints