Cost Optimization Python Packages

skypilot

Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, Slurm, 20+ clouds, on-prem).

metaflow

Build, Manage and Deploy AI/ML Systems

skypilot-nightly

Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, Slurm, 20+ clouds, on-prem).

metaflow-stubs

Build, Manage and Deploy AI/ML Systems

claude-code-llm-router

Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain keeps costs 70–85% lower.

cafitac-hermit-agent

Quiet MCP executor for Claude Code and Codex. Offload edits, tests, refactors, and commits to cheaper local or flat-rate models.

trainy-skypilot-nightly

Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, Slurm, 20+ clouds, on-prem).

pyoptex

Flexible and accessible design of experiments in Python. Provides industry with an easy package to create designs based with limited expert knowledge. Provides researchers with the ability to easily create new criteria and design structures.

attune-ai

AI-powered developer workflows with cost optimization and multi-agent orchestration

uncommon-route

Automatic LLM router — 82% cost savings, 79.4% accuracy, 93.4% pass rate. Drop-in OpenAI proxy.

attune-help

Lightweight .help/ runtime reader with progressive depth. Python package for the attune-docs help platform.

attune-author

AI-powered developer workflows with cost optimization and multi-agent orchestration

nocturnusai

Verified knowledge for AI agents. Compress context, extract and store facts, define rules, and ask questions — get deterministic answers with proof, not LLM guesses. Connect agents via MCP, Python SDK, TypeSc

monk-ai

Find hidden cost leaks and blind spots in your agentic AI workflows — 15 deterministic detectors, LangGraph support, team usage CSV analyzer, live dashboard, workflow simulator

ondine

Batch-process tabular data with any LLM. pandas & Polars in, structured columns out. Checkpointing, budget limits, and 100+ providers built in.

sqz

Compress LLM context to save tokens and reduce costs

kosty

AWS Cost Optimization & Security Audit CLI Tool - Identify cost waste, security vulnerabilities, and compliance issues across 16 core AWS services

empathy-framework

⚠️ DEPRECATED: This package has been renamed to attune-ai. Install attune-ai instead.

llm-routing

Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain keeps costs 70–85% lower.

tok-protocol

tok is an invisible bridge

frostwatch

AI-powered cost and query observability for Snowflake

train-in-silence

The first Task-Aware MCP server and automated VRAM calculator for LLM fine-tuning. Instantly snipe the cheapest, fastest GPUs across 10+ cloud providers.

leanctx

Drop-in prompt compression for production LLM applications. Cut Anthropic / OpenAI / Gemini bills by 40-60%.

promptrouter

Reduce your LLM costs by 40-70% automatically. Routes prompts locally, compacts context, tracks real savings.