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

finops-mcp

Local-first, AI-native FinOps. Ask your AWS, Azure, GCP, Kubernetes, and SaaS bill anything inside Claude or Cursor. Runs on your machine; credentials never leave it.

attune-ai

Attune-AI is a spec-driven meta-orchestration framework designed to establish a deterministic alignment layer between autonomous LLM agents and a production codebase.

distil-llm

Compression with a quality contract — cache-aware, causally-pruned LLM context compression for agentic runtimes, certified non-inferior across 7 domains. Works with any SDK.

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-author

AI-powered .help/ template authoring pipeline. Python package for the attune-docs help platform.

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.

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.

xrouter-llm

A prompt-aware LLM router that predicts which models can complete each request, then selects the cheapest capable one: 53.2% lower cost and +1.9 pts completion on our tested dataset.

empathy-framework

Attune-AI is a spec-driven meta-orchestration framework designed to establish a deterministic alignment layer between autonomous LLM agents and a production codebase.

trainy-skypilot-nightly

SkyPilot: An intercloud broker for the clouds

opencloudcosts

Anchor AI FinOps to real, live cloud pricing — open source MCP server for AWS, GCP, and Azure

cafitac-hermit-agent

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

leancontext

Trim the redundant tool output your AI agent re-sends every turn. Deterministic, type-aware token reduction with a fidelity score — never breaks the agent.

nadirclaw

Open-source LLM router & AI cost optimizer. Routes simple prompts to cheap/local models, complex ones to premium — automatically. Drop-in OpenAI-compatible proxy for Claude Code, Codex, Cursor, OpenClaw. Saves 40-70% on AI API costs. Self-hosted, no middleman.

frugon

Free, local, open-source LLM cost analyzer — see where your LLM bill leaks, on your machine.

sparecores-crawler

Pull and standardize data on cloud compute resources.

tokenxray

Live cost alerts, hard-stop ceiling, and session analysis for Claude Code. The spending guard Claude Code doesn't ship with.

s4-codec

GPU-accelerated transparent compression S3-compatible storage gateway. Drop-in replacement for AWS S3 endpoints; cuts your S3 bill 50-80% with no app changes (Rust, nvCOMP, zstd).

agy-headless-bridge

Call the Google Antigravity CLI (agy) headlessly from any non-TTY context — Windows ConPTY + POSIX pty + MCP server. Fixes the empty-output bug (#76).

s4fs

GPU-accelerated transparent compression S3-compatible storage gateway. Drop-in replacement for AWS S3 endpoints; cuts your S3 bill 50-80% with no app changes (Rust, nvCOMP, zstd).