Havuz

ChatGPT 模型路由检测器：查看服务器报告的真实响应模型，自动识别路由降级，GPT Pro 计划降智查询。｜ChatGPT Model Route Inspector: view the actual response model reported by the server

Engineering deterministic, production-grade systems around non-deterministic LLMs — FSM, durable execution, retries, DAGs, agent runtimes, m

Local Anthropic-compatible AI gateway with cheap-first routing, quality gates, safe model handoffs, and an embedded cost dashboard.

Route complex Codex tasks to model-specific background workers with bounded concurrency and lead-agent verification.

Self-hosted, Docker-first OpenAI-compatible LLM gateway with provider routing, fallbacks, API keys, and usage controls.

Session-scoped GPT-5.6 agent routing for Claude Code

Personal, local-first desktop AI gateway for Windows, macOS, and Linux. Connect Claude Code, Codex, and Gemini CLI to OpenAI, Anthropic, Gem

Quality-per-token GPT-5.6 Sol, Terra, and Luna model router for Codex, Work, CLI, and subagents.

Turn Fable or Opus into your agent orchestrator: plan coding work, assign capable Claude, Codex, or Grok agents, and personally verify the r

Open-source Codex plugin for Sol-governed multi-agent coding, bounded AI code review, model routing, and LLM cost optimization

OpenCode agent configuration — a read-only orchestrator delegates to 6 specialized subagents. Expert model plans, fast models execute. Isola

Portable model routing for Claude Code, specialized agents, ship gates, and Codex.

Tech-lead orchestration for Claude Code — the top-tier model (Fable) keeps architecture & decisions, cheap subagents (Sonnet/Opus) do the ro

Open-source AI CLI and local MCP server connecting 25 clients—Claude Code, Cursor, Codex, ChatGPT, Hermes, and OpenClaw—to 2,000+ models/API

Provider-pluggable orchestration runtime for multi-model AI inference. ( Sakana Fugu style )

Open-source Fugu: the open-source LLM orchestration brain.

把多模型 Provider、本地密钥和 HeavySkill 讨论统一成 MCP 网关 | Local MCP gateway for multi-provider LLM routing, secrets, and HeavySkill discussions.

A prompt-aware LLM router that predicts which models can complete each request, then selects the cheapest capable one: 53.2% lower cost and

Self-hosted LLM gateway — route OpenAI/Anthropic/Gemini traffic by config, not code. Fallback, protocol translation, telemetry.

TRINITY in Elixir (An Evolved LLM Coordinator): route LLM calls via a small-model hidden-state router + Axon coordination head, with Thinker

Cheap Money-Saving Self-hosted AI agent workspace with tool calling, MCP, multi-model routing, sandboxed execution, multi-agent workflows, a

Stateless LLM runtime that dynamically routes, loads, executes, and unloads models per request with bounded VRAM caching and intelligent mod

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

Private AI assistant, AI agent, and unified model proxy for Claude Code, Codex CLI, Gemini CLI & OpenClaw. Skills, MCP, tools, channels, tas

OpenVitamin is a local-first AI execution platform that unifies Agents, Workflows, and multi-model inference into a single programmable syst

🏆Winning Project | ModelGate is a contract-aware AI control plane that ingests customer contracts, extracts SLA/privacy/routing constraints,

Auto-delegation, status truth, and cost-aware model routing for OpenClaw agents

Automatic LLM router — 82% cost savings, 79.4% accuracy, 93.4% pass rate. Drop-in OpenAI proxy.

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