BlockRunAI/ClawRouter

Drop-in LLM router and AI gateway speaking OpenAI Chat Completions, OpenAI Responses and Anthropic Messages APIs, with 124 routing strategies across GPT-6 Astra, Claude Opus 5.5, Gemini 4 Argon and Kimi K3.1 Pro, plus budgets, fallbacks, tenant rate limits, idempotency and audit logs.

ClawRouter for Hermes — BlockRun's full LLM catalog incl. Claude, GPT and Grok; x402 USDC micropayments on Base & Solana. Python plugin wrapping the ClawRouter proxy for NousResearch/hermes-agent.

Self-hosted LLM gateway that routes requests across AI providers (OpenAI, Anthropic, Gemini, Mistral, Ollama) using intelligent multi-policy scoring — including an LLM-native routing policy. Drop-in compatible: just swap the base URL. No database required, built-in cost tracking, budget enforcement and multi-tenant isolation.

A self-hostable LLM router / gateway: OpenAI- and Anthropic-compatible, explicit-first routing with fallbacks, spend limits, and metadata-only cost tracking. No markup, no third-party proxy — your keys, your box.

Self-hosted LLM router with a managed safety net. OpenAI-compatible. BYOK. Single-workspace. Streaming. For more advanced routing choose hosted OrcaRouter

Route every request to the cheapest model that can handle it and save 70%+

Open Source LLM Gateway 🦚

Local LLM API Intelligent Gateway — Open-source client + Server Open Core model, unified management of multiple LLM Provider channels, providing intelligent routing, session stickiness, cost optimization, full-chain observability, and team collaborative governance.

A framework for serving and evaluating LLM routers - save LLM costs without compromising quality