faraa2m

@ast-ai-model-router/cli

AST-based Claude Code and Codex model router with token-cost estimates, CI policy checks, and explainable AI coding-agent model selection.

@promptc/cli

CLI for promptc.

@promptc/codegen

Codegen from promptc IR back to target output formats.

@promptc/ir

Prompt IR types and utilities for promptc.

@promptc/parser

Parsers (markdown / XML / plain) into promptc IR.

@promptc/passes

Deterministic optimization passes for promptc IR.

@routerlab/cli

CLI for routerlab — cost-quality routing for LLM APIs.

@routerlab/core

Routing engine for cost-quality LLM model selection.

tokenometer

Tokenometer CLI — LLM token cost + latency benchmarking across Claude, GPT-4o, Gemini, Mistral, and Cohere. Multi-format, empirical mode, vision tokens, SARIF output.

@tokenometer/core

Tokenometer core library — multi-provider LLM token cost, latency, and vision-token estimation with empirical countTokens fallback (Anthropic, OpenAI, Google, Mistral, Cohere).

@tokenometer/mcp

Model Context Protocol server for tokenometer — lets AI agents self-monitor LLM token spend, estimate costs, and budget-check before sending prompts.