- Conduid
- Marketplace
- #llm-routing
MCP servers tagged llm-routing
19 live MCP servers tagged "llm-routing", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with llm-routing.
Ratel
Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 retrieval. No vector DB. No embeddings.
Agentweave
Pre-inference tool and agent routing for MCP, A2A and tool-rich LLM systems. Reduce candidate tools before model inference with policy-aware routing and recovery.
TrustGate
Open-source AI gateway for LLM and agent traffic — multi-provider routing, guardrails, semantic caching and MCP support. Written in Go.
Trustgate
Open-source AI gateway for LLM and agent traffic — multi-provider routing, guardrails, semantic caching and MCP support. Written in Go.
Deltallm
Route, manage, and analyze your LLM requests across multiple providers with a unified API interface
StackFerry
A focused desktop provider manager and router for AI coding tools.
Jev Style
Small, calibrated decision models on your own machine: systemone-compatible local server, 6 agent skills, Claude Code guard, MCP tools. Weights on Hugging Face.
Gutcheck
Fast, calibrated System-1 decisions (Jev/Laya-style) on your NPU/GPU, plus per-prompt skill & MCP tool leasing that cuts agent context ~99%.
Codex ChatGPT JEV Switch
Fork of codex-with-chatgpt: TypeSafe Jev + deterministic rules decide when Codex hands work to ChatGPT web (plan, debug, review) and when it switches back. 用 Jev 自动决定 Codex 与网页版 C…
ThinkLess
The decision plane for AI agents. Rules and small calibrated models make the routine decisions, the LLM is reserved for the steps that need thought, and every step is traced.
Quay
Quay — Autonomous AI Software Factory. Self-hosted AI agents, MCP integration, customizable pipelines, and real-time Mission Control.
Claude Local Stack
Claude Code stack for Apple Silicon — multi-profile LLM routing (local MLX, Bedrock, Anthropic), token compression, MCP integration
Trantor
The hub-world for AI agent crews — orchestrate Claude Code, Codex, Gemini, Kimi & DeepSeek as live crews with a plan-aware Advisor, a Kanban/flow command center, a testing gate, a…
Sovereign Projects
Maximal sovereign workspace layer and monorepo
Omnibridgemcp
OmniBridge is an MCP server that gives AI agents an ephemeral, gVisor-isolated sandbox to run, test, and cryptographically prove their code works — before it ever reaches producti…
Codex Deepseek Visible Stream
Deploy and route DeepSeek V4 Pro/Flash inside Codex with Sol/Luna orchestration, 30-second async polling, and budget-safe local answer paging.
Hoheit
Vendor-neutral AI orchestration endpoint - OpenAI-compatible, with explainable routing across cloud and local models, YAML agents and MCP tools. Self-hosted.
Jev Codex Router
Experimental TypeSafe Jev model routing for Codex Desktop: per-task model and reasoning selection, complex-task planning, subagent dispatch, and fallback.
RepoMind
AI-powered codebase intelligence platform that combines RAG, code-aware indexing, GitHub MCP, LangGraph, and multi-provider LLM routing to understand and answer questions about re…