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

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).

claude-code-llm-router

DEPRECATED: Use 'llm-routing' instead. This package provides redirect to the new package.

attune-ai

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

tokenxray

See where your AI coding tokens actually go.

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.

uncommon-route

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

attune-author

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

ondine

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

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.

attune-help

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

baar-core

Budget-Aware Agentic Routing (BAAR) — Intelligent LLM model selection with a zero-call financial kill-switch. Save 90% on costs without losing accuracy.

tok-protocol

tok is an invisible bridge

empathy-framework

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

frostwatch

❄️ Open source, self-hostable AI-powered cost and query observability for Snowflake. Snowflake cost monitoring shouldn't cost more than the savings.

sqz

Compress LLM context to save tokens and reduce costs

nocturnusai

Python SDK for NocturnusAI — a logic-based inference engine and knowledge database

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.

smartmemo

Semantic memory and caching for LLM agents with classifier-validated equivalence instead of naive cosine thresholds.

kosty

Scan 30+ AWS services. Find cost waste. Detect security gaps. Map your attack surface. One command.