offline-ai/cli
The AI agent script CLI for Programmable Prompt Engine.
Built on the Programmable Prompt Engine specification, this CLI executes YAML-based agent scripts with pluggable LLM backends—supporting local inference via llama.cpp (with automatic GPU detection and memory optimization), OpenAI-compatible APIs, and inter-script function calls. Key capabilities include intelligent result caching, tool invocation without model-specific training, structured output parsing (JSON/YAML/NOBJ schemas), and dual-permission tool access control between scripts and users.
Available on npm.
Stars
77
Forks
9
Language
TypeScript
License
—
Category
Last pushed
Oct 24, 2025
Monthly downloads
54
Commits (30d)
0
Dependencies
20
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/offline-ai/cli"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
microsoft/promptflow
Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.
pezzolabs/pezzo
🕹️ Open-source, developer-first LLMOps platform designed to streamline prompt design, version...
promptdesk/promptdesk
Promptdesk is a tool designed for effectively creating, organizing, and evaluating prompts and...
cremich/promptz
Resource Library for AI-assisted software development with kiro
scafoldr/scafoldr
Building an open-source alternative to v0 and Lovable.