Mirascope/mirascope
The LLM Anti-Framework
Provides a unified Python and TypeScript interface across multiple frontier LLMs (Claude, GPT, etc.) using simple decorators for calls, structured output via Pydantic models, and agentic tool use with automatic execution loops. Built on a lightweight abstraction layer that avoids opinionated framework patterns, enabling streaming, async, and multi-turn conversations while maintaining provider-agnostic code.
1,425 stars and 51,874 monthly downloads. Used by 1 other package. Actively maintained with 29 commits in the last 30 days. Available on PyPI.
Stars
1,425
Forks
108
Language
Python
License
MIT
Category
Last pushed
Mar 11, 2026
Monthly downloads
51,874
Commits (30d)
29
Dependencies
5
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/Mirascope/mirascope"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related tools
langfuse/langfuse
🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management,...
Arize-ai/phoenix
AI Observability & Evaluation
Helicone/helicone
🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓
Agenta-AI/agenta
The open-source LLMOps platform: prompt playground, prompt management, LLM evaluation, and LLM...
algorithmicsuperintelligence/optillm
Optimizing inference proxy for LLMs