# Mirascope/mirascope

The LLM Anti-Framework

Repository: https://github.com/Mirascope/mirascope
Canonical: https://ross.abutalabs.com/products/mirascope
Homepage: https://mirascope.com
Language: Python
License: MIT
License Family: permissive
Topics: artificial-intelligence, developer-tools, llm, python, llm-agent, llm-tools, typescript
Last push: 2026-08-19T00:15:31+00:00

## Health v2 (maintenance only)
Score: 86/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 98, release rhythm 78, longevity 71
- inputs: {"age_days": 1003, "days_push": 15, "days_rel": 70, "gap_med": 2.0, "n_releases_24m": 97}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1522, forks 125 (observed 2026-08-28T04:04:57.918178+00:00)

## What it is
Mirascope is a Python (and TypeScript) library providing a unified, provider-agnostic interface for calling frontier LLMs like OpenAI, Anthropic, and Google models. It offers decorators for LLM calls, structured outputs via Pydantic, tool-based agent loops, and built-in tracing, versioning, and cost tracking.

## Use cases
- call any LLM provider with one unified interface
- get structured output from LLM responses with pydantic models
- build agents that use tools and multi-turn loops
- add tracing and cost tracking to LLM calls
- stream LLM responses and handle async calls
- switch between OpenAI, Anthropic, and Google without rewriting code

## When to choose
- you want a lightweight, decorator-based LLM abstraction without heavy framework lock-in
- you need structured outputs and tool-calling agents across multiple providers
- you want built-in observability like tracing, versioning, and cost tracking

## When to avoid
- you need a full agent framework with orchestration, memory, and RAG pipelines out of the box
- you work primarily outside Python or TypeScript
- you prefer direct provider SDKs with no abstraction layer

## Facets
- artifact type: library
- maturity: active
- function: llm-inference, agent-framework, prompt-engineering, sdk, tracing, middleware
- domain: large-language-models, developer-tools, artificial-intelligence
- platform: python, cross-platform
- tags: llm, unified-interface, structured-output, llm-tools, provider-agnostic, observability, anti-framework, ai-agents, retrieval-augmented-generation

## Member repositories
- Mirascope/mirascope (main) score 86

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:57.918178+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:31:46.071069+00:00, confidence not recorded.
  - readme: https://github.com/Mirascope/mirascope (fetched 2026-08-28T04:04:57.918178+00:00, sha f689b3bee930)
  - homepage: https://mirascope.com (fetched 2026-08-29T11:34:40.613115+00:00, sha d50ff50cc8e8)
  - site_page: https://mirascope.com/docs (fetched 2026-08-29T11:34:40.616125+00:00, sha b24e2878378e)
  - registry_pypi: https://pypi.org/pypi/mirascope/json (fetched 2026-08-29T11:34:40.618033+00:00, sha f9f80a9ebce5)
- Data as of 2026-08-30T08:39:29.467469+00:00.