LLMForge - Autonomous AI Engineering, LLM Evals, Fine-Tuning & Inference Cost Engine MCP

Description

Universal AI engineering engine for Cursor, Claude Code & Windsurf. Architects complete LLM blueprints (prompting vs RAG vs fine-tuning vs agents matrix, model selection with token cost projections), builds eval harnesses (golden datasets, LLM-as-judge with bias controls, CI regression gates), produces fine-tuning recipes (LoRA/QLoRA configs with concrete hyperparameters, honest should-you-finetune gates, distillation paths), slashes inference bills 50-90% (cascade routing, prompt caching, batch APIs, self-host break-even math), and hardens LLM features for production (prompt injection defense, fallback chains, red-team checklists, incident runbooks). NEW v1.1 - compare_llm_prices_live: Compares REAL current prices across 450+ LLMs live via the OpenRouter market: cost per 1M tokens, context windows, cheapest and free models.

Community Metrics

Categories

• mcp

Tags

• mcp
• smithery

Capabilities

• remote

Information