JarvisPei/SCOPE
SCOPE: Self-evolving Context Optimization via Prompt Evolution - A framework for automatic prompt optimization
Learns from agent execution traces using a dual-stream memory system that separates task-specific tactical rules from reusable strategic guidelines, with automatic memory optimization via conflict resolution and subsumption pruning. Integrates with 100+ LLM providers through LiteLLM (OpenAI, Anthropic, etc.) and provides a universal async API for injecting evolved prompts into agent workflows. Features Best-of-N candidate selection, configurable synthesis modes, and customizable prompt templates to adapt SCOPE for specialized agent domains without modifying core code.
Stars
70
Forks
6
Language
Python
License
MIT
Category
Last pushed
Dec 18, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/JarvisPei/SCOPE"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
linshenkx/prompt-optimizer
一款提示词优化器，助力于编写高质量的提示词
Undertone0809/promptulate
🚀Lightweight Large language model automation and Autonomous Language Agents development...
CTLab-ITMO/CoolPrompt
Automatic Prompt Optimization Framework
microsoft/sammo
A library for prompt engineering and optimization (SAMMO = Structure-aware Multi-Objective...
Eladlev/AutoPrompt
A framework for prompt tuning using Intent-based Prompt Calibration