z-ai-delegation

What problem does it solve?

Token economy: delegating generation to cheaper models (Z.AI, Gemini, Ollama) through LLM Rotation to minimize output-token consumption while preserving quality.

Core Features & Use Cases

• End-to-end delegation workflow: split tasks, delegate to Z.AI, perform review, and assemble final content to save tokens.
• Flexible signaling and levels: categorize tasks as Soft/Medium/Hard/Never and orchestrate across providers with guardrails.
• Use cases: drafting briefs, docs, and knowledge content where token budgets are tight and speed is valuable.

Quick Start

Describe the initial task to decompose, delegate to Z.AI, review results, and assemble the final content.