Search Packages

neuralbrok

NeuralBroker — A VRAM-aware LLM router. Daemon polls GPU every 500ms, routes requests to local Ollama or cloud Groq based on real-time VRAM state. Single OpenAI-compatible endpoint at localhost:8000

kalibr

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

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.

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.

syrin

Python library for building AI agents with budget management, declarative definitions, and production-ready observability.

llm-cost-reduction

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

llm-cost-optimizer

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

hyperion-ai

The official Python SDK for the Hyperion AI Gateway

livekit-ai-switchboard

Intelligent LLM routing for LiveKit voice agents

langchain-kalibr

The first autonomous routing system for AI agents. Routes to the optimal execution path to prevent failures, degradations, and cost spikes before they impact users.