- Conduid
- Marketplace
- #openai-compatible
MCP servers tagged openai-compatible
214 live MCP servers tagged "openai-compatible", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with openai-compatible.
Visbridge
Token-efficient vision capability layer for MCP clients (describe / OCR / inspect)
Opencode Devtools
MCP server for @vymalo/opencode-devtools — exposes the same local developer utilities (math, codec, crypto, datetime, convert, http) over the Model Context Protocol so any MCP cli…
Core
Stateless, task-oriented AI agent core
Autonomous AI Agency
An AI-powered workforce platform that executes multi-agent tasks with automatic provider failover and CEO agent orchestration. It detects technology stacks across 1,000+ platforms…
Nova Agent
轻量自包含的开源 AI Agent 教学项目：agent loop / MCP 工具 / Agent Skills / 定时任务 / 多 Agent 管理，代码可一晚读完。Lightweight self-contained AI agent for learning agent engineering: agent loop, MCP tools, Ag…
Foreman
Runs software missions unattended and shows you everything when you're back. A director plans, delegates to workers, verifies. Any provider, honest cost, defaults for every ask, y…
Projectdavid Core
Self-hostable LLM agent runtime
Wechat AI Assistant
可执行任务的微信/桌面 AI 智能体：LangGraph · MCP · RAG · Tauri
Dvara
AI Governance Platform - LLM Gateway, MCP Gateway, A2A Gateway.
Zalo Agent
Self-hosted AI agent living inside Zalo (personal account). Multi-account, 15 tools + external MCP servers, web dashboard, scheduler, durable memory, rich-text messages. Provider-…
CoworkerAPI
Local gateway exposing OpenAI- and Anthropic-compatible endpoints backed by ChatGPT through an official MCP widget.
Rei
Rei Agent. A local-first agent you assemble yourself.
Browser LLM API
OpenAI-compatible API over your signed-in ChatGPT and Gemini web sessions: chat, vision, image generation, and design tools that make website sections, app screens and brand image…
Mininaru
An LLM harness in one Go binary
Gateway
Behavioral scoring for AI agents. Observe every action, stop what deviates, prove what happened. Observe in 5 minutes, enforce when ready.
Crux
CRUX MCP - implying your system resolves the core problem of AI design slop. that targets engineering teams.
Rag LLM Wiki Knowledge Base
Self-hosted RAG x LLM Wiki knowledge base framework: document parsing/chunking/vectorization, knowledge graph, hybrid retrieval (vector + graph), multi-tenant API-key isolation, s…
TheYgent
No-code, local-first studio for building and running production ready AI agents. Inference runs on your machine — llama.cpp, MLX, or vLLM — or any OpenAI-compatible API you regist…
Pi T3chat
pi-t3chat t3.chat extension for Pi coding agent. 50+ frontier AI models (Claude Fable-5, GPT-5.6, Gemini 3.5, Grok 4.3, DeepSeek V4, Llama 4, Qwen 3) via t3.chat subscription. TL…
Demeter
Assistant IA souverain multiplateforme intégrant Albert, les API compatibles OpenAI, le RAG avec Qdrant et les serveurs MCP.
Impossible Inference
A self-hosted token-completion server for local open models, with chat and completion APIs, SSE streaming, WebSockets, gRPC, MCP and verified setup.
Hermes Pocket
Hermes Agent on your phone — runs fully on-device (no server, no root) or connects to your own server. Kanban, MCP, skills, built-in Linux.
AI Runtime Platform
AI Infrastructure OS execution plane: OpenAI-compatible gateway, MCP tool governance, intent proxy, vLLM/KServe/KEDA, OIDC, Redis and telemetry.
Adept Agentic
ADEPT: Agentic Discovery and Exploration Platform for Tools — A three-tier secure framework for multi-agent scientific workflows with 28+ MCP tools, 10 client interfaces, and decl…
Agentic Lab
A lab exploring agentic AI for Cloud and DevOps, built as small, runnable demos. Work in progress.
LatticeAI
Local-first private AI memory layer / Digital Brain for conversations, documents, decisions, and model-agnostic knowledge.
Claude Ds
用 DeepSeek V4 跑 Claude Code -- 一样的体验，几分之一的价格 | Drop-in DeepSeek V4 backend for Claude Code
AI Memory Hub
Local-first shared memory for AI agents, with MCP and HTTP APIs.
SpecterChat
Lightweight cross-platform desktop chat client for OpenAI-compatible APIs: MCP tools, image generation and editing. Built with Flutter.
L2MAS
Live2D multi-agent animation prototype with MCP, A2A, provider routing, local AI, ComfyUI/Ollama/vLLM, and FFmpeg.
FlashAgent
The coding agent built for local models. One native binary for your terminal that finds the model your local server has loaded, and tells you whether that model can actually drive…
Freegem
Local bridge exposing the Gemini web session as an OpenAI-compatible API, a Google-native API, and MCP tools, with a guarded web scraper and cited research.
AI Ducpt
Free shared AI gateway, OpenAI compatible, sign up at ai.ducpt.com / Cổng AI dùng chung miễn phí, đăng ký tại ai.ducpt.com
Pinterest Vision MCP
Visual intelligence pipeline for AI agents — search Pinterest, analyze with LLM vision, store and retrieve by semantic similarity
Tsm Hub
AI Capability Hub & LLM Gateway - unify models, tools, skills, MCPs, sandbox, memory with discovery and promotion across 13+ providers
Workbuddy Bridge
Use a WorkBuddy desktop account as an OpenAI- and Anthropic-compatible API for Claude Code, Codex, and any coding agent.
Prompt Boost
Open-source one-key prompt enhancement engine — turn vague ideas into structured task specs anywhere you type to an AI. CLI · MCP server · playground. Zero dependencies, BYOK, off…
Omniswarm
Self-hosted trust layer for cheap AI: offload bulk LLM work to free models, QC'd by a multi-model council — a vetted answer + confidence verdict at $0. OpenAI-compatible.
Rinari CLI
Rinari CLI — tu asistente personal de IA en la terminal: atenta, cariñosa y demoledoramente eficiente. Chat REPL + agente de código autónomo con control de git, búsqueda web y MCP…
bridgenode-ai/bridgenode-mcp
y @bridgenode/mcp` or remote `https://bridgenode.cc/mcp`.
Prompt Contract
Open-source one-key prompt enhancement engine — turn vague ideas into structured task specs anywhere you type to an AI. CLI · MCP server · playground. Zero dependencies, BYOK, off…
Local AI Agent
AgentTrail is a local-first AI agent layer for Ollama/local models that shows its work: semantic search, diff-safe edits, receipts, replay, memory, MCP, reports, and trust control…
Coracle
Personal-machine AI orchestrator: routes work between free-tier big AI (Gemini/Groq/Ollama Cloud + browser fallbacks) and local Ollama models (qwen2.5 + qwen2.5-coder) with a sing…
Bridgenode SDK Ts
BridgeNode — x402 pay-per-request AI inference. TypeScript SDK.
Modeldesk
本机多模态 AI 配测台，支持模型对比与 OpenAI 兼容网关。
Cingulater Old
Cingulater is an autonomous AI agent execution engine that self-heals LLM inference streams in real-time to ensure task completion. It features full OpenAI API compatibility and s…
LLM Offload
Claude の軽量な LLM 作業（要約・分類・抽出・簡単な質問）を、ローカルモデルや任意の OpenAI 互換プロバイダ（LM Studio・Ollama・OpenRouter・Grok・OpenAI・Groq・Together…）へオフロードする MCP サーバー | MCP server that offloads light LLM work (…
Openchatci
The localhost AI Agent Runtime -- Chat UI, Tools, RAG, and MCP in one pip install
TokLedger
The local inference ledger -> a zero-dependency OpenAI-compatible proxy that prices every request your home GPU serves: tokens, TTFT, tok/s, kWh, local $ and cloud-equivalent cost.
TangleBrain
A local-first, config-driven LLM router across OpenAI-compatible backends you own.