Mirascope

Python and TypeScript toolkit for calling any frontier LLM through one interface, with tools, structured output and tracing.

Harness by Mirascope

IndexedMIT★ 1,535

Write a review

Install

From the package registry. Read the repository before you give any tool access to your data.

pip install mirascope

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Mirascope gives one interface for calling LLMs from providers such as OpenAI, Anthropic and Google. Calls are declared with a decorator, responses can be parsed into Pydantic models, and a loop can execute tool calls and resume the model. The docs describe tracing, versioning and analytics as built in through OpenTelemetry. The repository is a monorepo that contains Python and TypeScript implementations.

Use cases: model-inference

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Languages: Python, TypeScriptREADME
Packages: mirascope (pypi)README
Streaming: YesREADME
Observability: OpenTelemetrymirascope.com
Model providers: openai, anthropic, googlemirascope.com
Maturity: Stablemirascope.com

Facts extracted by Claude Haiku 5.5 from the linked sources on Oct 24, 2026. Wrong fact? Tell us.

Alternatives

Frameworks for the same language with a similar way of orchestrating agents.

Signals

Stars: 1,535
Forks: 139
Open issues: 2
Weekly downloads: 5,831
Last commit: Oct 24, 2026 (5 days ago)
Last release: Oct 22, 2026 (6 days ago)
Last package publish: Oct 22, 2026 (6 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Packages: pypi mirascope
License: MIT
Repository: github.com/Mirascope/mirascope
Website: mirascope.com/
Docs: mirascope.com/docs
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: README Website Docs github-graphql