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.

Route inference across LLM providers. Track cost per request.

OpenVitamin is a local-first AI execution platform that unifies Agents, Workflows, and multi-model inference into a single programmable system — designed for building real, production-grade AI applications.

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!

Developer-first Python framework for AI agents with built-in budget control, context, memory and observability.

Claude Code hooks that auto-switch model tier based on task complexity

Your agents silently degrade in production. Kalibr keeps them on the optimal path — scoring every call, learning what works, routing automatically.

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

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.

Production-ready AI agent framework — semantic memory, multi-agent mesh, MCP server, intelligent routing, governance, and 67+ platform integrations.

Works for you. Go outside and live. — AI orchestrator that auto-routes tasks to the cheapest model that solves them. 70% run free on local models. Self-auditing, self-improving, zero prompting skill needed. Built with vibe coding by a finance student. Your models, your data.

Multi-protocol AI proxy server for Claude Code, Codex CLI, Gemini CLI & OpenClaw. Account pooling, API key management, free model routing, and visual dashboard.

Open-source Agent OS in Rust for long-running autonomous workflows: memory, tool sandboxing, and multi-provider LLM routing.

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.

Route every prompt to the best LLM — for you specifically.

OpenClaw Model Router Plugin - Natural language model routing rules via slash commands. Delegate tasks to subagents with the right model, no token waste.

The Claude Code discipline layer. Cost tracking, git hygiene, session telemetry, TDD nudge, subagent awareness, PR size gating, and SDLC compliance — installed with one command.

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

One interface, every model at your command. Your local AI routing butler. | 一个接口，万模随心。你的本地 AI 智能路由管家。 | Built for OpenClaw & AI agents.