OpenAI-compatible dynamic LLM router — a single Go binary, installed via npm as a prebuilt native binary

OpenClaw plugin for UncommonRoute, the local LLM router that cuts premium-model spend

Ollama agent router and local LLM router for OpenAI-compatible model routing, GPU-aware queues, async jobs, and CLI configuration.

Zero-framework LLM router for Node.js — unified streaming, tool calling, and usage tracking across OpenAI, Anthropic, Google, Ollama, and any OpenAI-compatible provider.

MCP server integration for llm-router

Production-ready LLM router with load balancing, resilience patterns, and multi-provider support

Minimal OpenClaw-first LLM router.

Smart LLM router — save 85% on inference costs. 55+ models (11 free), one wallet, x402 micropayments.

CLI tool for llm-router

Route each Pi session's first task to an appropriate model

Smart LLM router — auto-routes requests to the best OpenRouter model

Multi-provider LLM routing with 3 orthogonal resilience states: rate-limit ≠ quota-exhausted ≠ circuit-broken. TypeScript port of the Python resilient-llm-router.

Research-backed Multi-LLM Router with parallel execution, learned routing (RouteLLM), prefix caching (RadixAttention), speculative decoding (Medusa/EAGLE), token compression (ISON), local LLM support (Ollama/vLLM/LM Studio), batch processing. Python bindi

Framework-free deterministic DAG orchestration core — TypeScript port of the llm-router planner/scheduler/validator/fusion pipeline

Core types, schemas, and validation for llm-router

Deterministic priority and fallback routing for text generation across Vercel AI SDK providers.

Tenant-scoped Knowledge Base: hybrid retrieval (pgvector + BM25), ingest, answer pipeline, persona/skill composition. LLM I/O живёт в @chatman-media/llm-router.

Smart LLM router via ZenMux — 100+ models, intelligent routing, token cost savings.

Self-hosted OpenAI-compatible LLM router that auto-imports providers from your OpenClaw config

Rule-based LLM router. Classifies queries across 8 axes and picks the optimal model. Fast, deterministic, zero dependencies.