Model Routing Python Packages

my-claude-code

My Claude Code (MCC) is a local multi-provider LLM proxy, model router and control plane for Claude Code, Codex, OpenCode, Gemini CLI and other AI coding agents — 57 providers, fallback routing, credential health, a native web-search tool proxy, and exhaustive analytics with cost provenance in one local dashboard.

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.

modelhop

Intelligent LLM router that saves 60-90% on API costs by hopping to the cheapest capable model

codai-sdk

Official Python SDK for codai - OpenAI-compatible client for the codai gateway. PyPI: codai-sdk

kalibr

Stop overpaying to run your agents. Kalibr routes every request to lower-cost model and tool paths without degrading performance.

latencyops

Provider-neutral AI inference latency measurement and quality-aware execution planning toolkit

evalt

Budget-bounded LLM routing that finds the cheapest model and prompt meeting your accuracy target.

claude-router

claude-router is a local prompt router that picks the right Claude model tier and prepends the right scaffold using local embeddings before you call the API. A deterministic routing layer for eval, research, content, and review prompts that helps teams stop overspending on Sonnet and Opus when Haiku plus structure is enough.

clef-router

Route prompts between cheap and frontier LLMs with Cloudflare's Clef decision model. OpenAI-compatible proxy + library.

nadirclaw

Source-available LLM router and AI cost optimizer. Routes simple prompts to cheap or local models and complex ones to premium models, automatically. Drop-in OpenAI-compatible proxy for Claude Code, Codex, Cursor and OpenClaw. Self-hosted, no middleman.

spacepilot

Autonomous model-to-production infrastructure

agentforge-oss

Open-source multi-agent orchestration with cost-awareness, security, and compliance built in. Anthropic, OpenAI, and offline providers.

ucci-router

UCCI: calibrated cascade routing for LLMs. Reference implementation of arXiv:2605.18796 (Python, CLI, Rust).

uncommon-route

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

langchain-router

Cost-aware model routing for LangChain agents. Routes execution turns to a fast model, keeps the expensive model for planning and recovery.

volante

Volante — a transparent, user-owned model router and orchestration control plane (alpha). Plans a task DAG, filters hard capabilities, then routes each sub-task across your configured models (Anthropic, OpenAI-compatible, Ollama, Claude Code, Codex) with a full, auditable decision trace. No LangChain/CrewAI/LiteLLM.

tiershift

Shift every LLM call to the cheapest model that can handle it. Routing decided by TypeSafe Jev in ~180 ms. No training data. Policy in plain YAML. TypeScript and Python.

arbiterx-gate

Your AI writes code. ArbiterX decides if it's good enough. Intelligent middleware for AI coding assistants — 97% token reduction, smart model routing, quality gate scoring. Works with Claude Code, Codex, Cursor, Copilot, Aider & more.

astrometron

Reproducible evaluation and evidence for AI systems: datasets, prompts, scorers, failures, cost and provenance.

llm-pqr

Provider-neutral LLM model selection using measured quality, latency, cost, capabilities, and hard privacy constraints.

python-rerouting-library

A lightweight Python library for semantic model routing between local quantized Llama on CPU and cloud LLMs with uncertainty handling and fallback.

syrin

The Python Harness for Production AI Multi-Agent Systems

langchain-model-router

In-process model routing for LangChain: a chat model that picks one of several candidate chat models per request.

crupier

Python orchestration SDK for routing, combining, and auditing AI model calls.