madara88645/Compiler
A tool that compiles messy natural language prompts into a structured intermediate representation (IR) and optionally sends them to LLMs like ChatGPT for cleaner, more reliable responses.
The compiler uses a multi-layer IR approach with policy-aware metadata (risk level, execution mode, data sensitivity) to enable safer downstream automation workflows. Core features include agent/skill generators with framework-specific exports (LangChain, Claude SDK, LangGraph), local SQLite-backed RAG for domain grounding, and GitHub artifact rendering—all controllable via a conservative mode toggle that prevents hallucination-prone expansion. A VS Code extension and browser plugin provide IDE integration with persistent settings and API key management via secure storage.
Stars
17
Forks
1
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/madara88645/Compiler"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Leonxlnx/agentic-ai-prompt-research
Research into how agentic AI coding assistants work — reconstructed prompt patterns, agent...
antonio0720/writing-intelligence
75 files. 76,327 words. The most advanced writing compiler ever open-sourced — now with a...
jefftriplett/files-to-claude-xml
Use XML tags for long context prompting using Claude's multi-document structure.
m727ichael/context-engineering
Information architecture for AI reasoning. PromptOS + HITL Context Engine. Copy, paste, use
yanzai-4/Contrix
Turn any LLM into a reliable local JSON API | Contract-first local LLM API builder for...