provider-routing

Codex 与 Claude Code 本地多供应商路由中枢：集成 CC Switch，支持即时切换、自动重试、Token 统计、健康监控与兼容传输。 Local provider hub for Codex and Claude Code.

Access the full OpenRouter catalog (400+ models) — chat, TTS, audio (input + generation), image-generation, video-generation, and embedding models — directly inside Open WebUI, with provider routing, reasoning tokens, streaming, fallbacks, native media rendering, and cache control out of the box.

Provider-agnostic multi-agent coding orchestrator in Go. Unified router for any LLM provider (Ollama local+cloud, OpenAI, Anthropic, Google Gemini) with role-based model assignment, fallback chains, and cost tracking. Inspired by gastown and LiteLLM.

Switch Claude Code between LLM providers — no proxy, no config editing

An OpenAI-compatible reverse proxy you run yourself. It gives you the features of an AI gateway (guardrails, budgets, rate limits, multi-provider routing) but under your control from your client.

One Rust binary for explainable AI provider routing: multi-provider fallback, encrypted credentials, budgets, quotas, and metadata-only traces — no client code changes.

🔄 Automatic LLM provider failover with circuit breaker. MiMo, OpenAI, DeepSeek. Zero deps.

Adaptive LLM router for 41 providers. Reorders routes on every request using observed quality, latency, health, and quota — powered by Thompson Sampling, with built-in routing observability and zero dependencies in the core.

Oberon — an AI film operating system: one-line brief into a full multi-shot production plan with 7-dimension scored model routing, continuity bible, camera choreography, and a deterministic title/caption render lane. Pure, deterministic, BYOK.

Personal operational Hermes Agent fork for local profiles, goal-loop, voice, compaction, and gateway reliability patches.

Minimal local-first AI runtime primitives for provider routing, executable resolution, atomic persistence, and workspace readiness checks.

Claude Code LLM gateway plugin for Swobu — connect once, then keep provider routing and failover behind one stable endpoint.

Experimental safety-first relay for Codex subagent tasks through third-party model providers.

🔄 Automatic LLM provider failover with circuit breaker. MiMo, OpenAI, DeepSeek. Zero deps.

DSH plugin that ranks OpenRouter providers by cost, speed, context, and reliability, then switches the active route.

A lightweight OpenAI & Anthropic compatible API gateway with intelligent provider routing, automatic failover, and streaming. Optimized for n8n AI Agents and Claude Code.

Personal AI software-engineering control plane for context, provider routing, token budgets, isolated Git worktrees, approvals, audit and REST/SSE.

Self-hosted multi-tenant .NET AI Gateway for unified AI provider routing, tenant API key isolation, fallback, rate limiting, metrics, and governed AI service access.

Mock-first multi-provider chatbot with opt-in provider routing; retrieval is not implemented.

AI Council that turns repos, notes & requirements into decision-ready PRDs/BRDs/SOWs, roadmaps, backlogs & traceable project knowledge. Multi-agent debate, 4-mode provider routing, knowledge graph, portable to any AI IDE.