Llm Routing Python Packages

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.

kalibr

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

cafitac-hermit-agent

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

ratel-ai

Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 retrieval. No vector DB. No embeddings.

switchboard-local

Privacy-aware, local-first router for your CLI coding agents (Codex, Claude Code) and local LLMs (Ollama) — keeps sensitive prompts on-device and cuts premium-model usage.

claude-wayfinder

Deterministic, auditable agent/skill dispatch for Claude Code. A typed seven-decision scoring kernel runs after the router has read the conversation — post-cognitive routing instead of prose-scanning. Auto-generates its catalog from skill sidecars and agent frontmatter.

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.

spekoai

Official Speko Python SDK (spekoai) - one API for every voice AI provider: STT, TTS, and LLM routing + failover, sync + async

split-stack

Route each agent step to the right local Ollama model. Zero-dep Python routing primitives for agent loops and gateways.

local-llm-router

Python routing library for local LLM agent loops: score prompts, map tiers to model names, embed in your runner.

ainfera

The Inference of AI Agents. Drain-proof wallets, signed AgentCards (JWS), hash-chained AuditChains — out of the box.

kvfleet

Production-grade, KV-cache-aware intelligent routing for self-hosted and hybrid LLM fleets.

warmwinter

Python SDK for the Warm Winter trust gate — is this AI/agent action trustworthy enough to act on, or escalate?

claude-router

Embedding-based scaffold router for Claude API. Routes tasks to the right scaffold using centroid matching. By Hermes Labs.

llm-cost-optimizer

Automatically reduce LLM API costs. Routes to cheapest model that succeeds. Use kalibr instead.

llm-cost-reduction

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

langchain-kalibr

LangChain integration for Kalibr. Route every LangChain LLM call to lower-cost model paths without degrading performance.

hyperion-ai

The official Python SDK for the Hyperion AI Gateway