OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Mirascope

Mirascope is an open-source Python and TypeScript framework for building LLM-powered applications. It provides a unified calling interface, structured-output handling and tools that let a model invoke application functions.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Mirascope — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Mirascope when you need framework-level building blocks for language-model calls, structured results or agents that invoke your own functions, and want to integrate those patterns into an application you develop.

Who it is for

  • Developers building LLM features into Python or TypeScript applications
  • Teams creating tool-using agents, structured-response workflows or conversational applications

Documented uses

  • Call a language model through a decorator-based interface and retrieve its response text.
  • Parse model output into a defined Pydantic structure, such as a book title and author.
  • Register application functions as tools, execute requested calls and resume the model response.
  • Build streaming, asynchronous or multi-turn applications using the documented framework capabilities.
  • Instrument agent execution with tracing and track prompt or agent changes with versioning.
Before you choose

Requirements & limits

The project is open source under the MIT License. Documentation shows installation with uv or pip; a provider API key is required for the illustrated model calls.

  • The repository contains separate Python and TypeScript implementations.
  • The quick-start installation uses the all package extra.
  • The documented examples include provider-specific model identifiers, so provider and model configuration should be checked against the relevant documentation.
  • Mirascope Ops documentation covers tracing and versioning alongside calls and tools.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Mirascope and prepare a provider key

Set up the documented package and provider credential before building an LLM application.

Before you start

  • Python package-management environment using uv or pip
  • An API key for the provider you plan to configure

Steps

  1. Install with the command below or the command below.

    Documented command
    uv add "mirascope[all]"
    Documented command
    pip install "mirascope[all]"

  2. Set the provider API key in the environment; the quick start illustrates OPENAI_API_KEY.

  3. Consult the provider configuration documentation for other providers.

Expected outcome

Mirascope is installed and a provider credential is configured for the next development step.

Guide limitations

  • This covers installation and credential setup, not execution of an application.
  • The documented examples show OpenAI key setup and an Anthropic call; they do not establish every provider/model combination.
Documentation 1 ↗Documentation 2 ↗
Evidence and transparency

Sources & review

Official repository ↗Guide documentation ↗
Source record details
Source availability
Active
Sources checked
3 October 2026
Original website title
Mirascope/mirascope · Official homepage title · retained in its source language
How we review sourcesSuggest a correction