Smart LLM router that cuts AI costs by 40-70%. Routes simple prompts to cheap/local models, complex ones to premium. Works with Claude Code, OpenClaw, Cursor. OpenAI-compatible proxy, runs locally.

Route inference across LLM providers. Track cost per request.

Intelligent model orchestration for Claude Code - routes queries to optimal Claude model (Haiku/Sonnet/Opus) based on complexity. It also includes many more features. If this project is working well for you and would like to support me, just help spread the word. Thanks!

Intelligent model routing for OpenClaw - Sonnet 4.6 vs Opus 4.6 based on task complexity

Free, self-hosted AI model router. OpenRouter / ClawRouter alternative using your own API keys. 14-dimension classifier routes to the right model (Anthropic/OpenAI/Kimi) automatically. No middleman, no markup. Built for OpenClaw.

Intelligent model routing for OpenClaw with quota prediction, task classification, and automatic optimization

An intelligent, low-latency local LLM router that reduces AI costs by 30-70%. Uses a self-hosted classifier to automatically route prompts to the most cost-effective model without external API overhead.

Scalable LLM cost enforcement middleware for Node.js with budget protection and multi-provider support

Zero-cost model routing for OpenClaw using subscriptions. Route tasks to the right model automatically.

An Agentic AI system for Deepfake Detection & Media Authenticity Verification. Features autonomous model routing, an ensemble of 6 specialized neural networks, and advanced bias correction mechanisms.

AI assistant that learns your workflows — auto-generates skills, routes to the cheapest LLM, and replays every execution. Telegram · Slack · Discord · Matrix. One Rust binary, zero setup.

An intelligent LLM inference gateway that dynamically routes user queries to optimal model tiers (Llama-3.1 8B/70B) based on real-time complexity, reasoning depth, and ambiguity analysis.

Cost-intelligent AI agent framework for TypeScript. Model routing, budget enforcement, multi-agent pipelines with crash recovery. Works with Claude, GPT, Gemini, and 40+ providers.

Intelligent model routing engine that analyzes customer specifications, scores complexity, and routes each request to the most cost-effective LLM. Up to 97% cost savings.

ARCHIVED: See openclaw-tactician for the active version

One place to define AI tasks and map tasks to models. Stop scattering ad-hoc LLM calls across the codebase and maintain visibility, control, and cost/performance by task type.

Model-agnostic LLM orchestration with multi-backend routing, agent loop with tool calling, and C-Suite integration

Multi-model router with intelligent routing, cost tracking, quality monitoring, and fallback chains