mkorpela/kopipasta
`cat project | LLM | patch`. Transparent context control and interactive patching for terminal-centric LLM workflows.
Implements a **four-state file selection model** (Unselected, Base, Delta, Map) to explicitly track context syncing across LLM turns, reducing token waste through skeleton summaries and preventing context drift via session memory (`AI_SESSION.md`). Supports **universal intake** for intelligent patch application and path extraction from LLM responses, plus **MCP server integration** (Ralph Loop) to sandbox agentic edits with read-only project context and verification-based self-correction.
Available on PyPI.
Stars
16
Forks
1
Language
Python
License
MIT
Category
Last pushed
Mar 01, 2026
Monthly downloads
672
Commits (30d)
0
Dependencies
13
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/mkorpela/kopipasta"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
shcherbak-ai/contextgem
ContextGem: Effortless LLM extraction from documents
ShahzaibAhmad05/gitree
An upgrade from "ls" for developers. An open-source tool to analyze folder structures and to...
mufeedvh/code2prompt
A CLI tool to convert your codebase into a single LLM prompt with source tree, prompt...
nicepkg/ctxport
Copy AI conversations as clean Markdown Context Bundles — one click from ChatGPT, Claude,...
WecoAI/weco-cli
The Platform for Self-Improving Code. Ideal for GPU kernels, ML model development, feature...