- Conduid
- Marketplace
- #edge-ai
MCP servers tagged edge-ai
40 live MCP servers tagged "edge-ai", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with edge-ai.
Olares
Open-Source Personal Cloud OS for Always-On Agents
Picoclaw
Ultra-lightweight, open-source, self-hosted personal AI assistant in Go for RISC-V, SBCs, and embedded systems. Active PicoClaw fork with WebUI, MCP, memory, multi-agent workflows…
OGAM
The Swiss Army Knife of Offline AI. Chat, see, speak, and generate images on your phone or Mac — GGUF LLMs, vision, Whisper speech-to-text, Stable Diffusion, tool calling, and loc…
Qdrant MCP Pi5
Persistent semantic memory for AI agents on Raspberry Pi 5 — local Qdrant + MCP, no cloud, ~3s per query
KrillClaw
The world's smallest AI agent runtime. 49KB. Written in Zig. Zero dependencies.
Agentic Engineering Infrastructure
Deploys your OS, databases, and SSL on your VPS in just 10 minutes. Orchestrates a team of AI agents for coding, marketing, and sales. The built-in optimizer saves up to 90% on to…
Agent Engineering Infrastructure
Deploys your OS, databases, and SSL on your VPS in just 10 minutes. Orchestrates a team of AI agents for coding, marketing, and sales. The built-in optimizer saves up to 90% on to…
AAOSP
[Archived] AAOSP, predecessor to JibarOS. Early experiment in OS-level on-device AI (MCP + local LLM on Android 15). See JibarOS for the active project.
Gomcp
🛡️ The only Open-Source RLM Memory Server with Mathematically Proven Safety. Persistent context, MCP tools & Sentinel Lattice protection for autonomous AI agents.
Edgesentinel Visionops
Jetson Nano edge AI vision Agent Harness: real-time video analytics, MCP tools, event evidence, DeepSeek online/offline, secure recovery
Bubbaloop
Open-source Hardware AI agent. Single Rust binary for cameras, sensors, robots, and IoT fleets — orchestrated by AI agents with memory and real-time telemetry. Runs on Jetson, Ras…
Edge Core
Self-hostable control plane for distributed Linux and edge fleets: WireGuard mesh, SSH proxy, remote execution, Prometheus metrics, events, and MCP over one API.
AAOSP
Agentic Android Open Source Project (AAOSP) — Android fork with native LLM system service, MCP-aware apps, and an agent-driven launcher. On-device Qwen 2.5 via llama.cpp. Apps dec…
Cockpit Agent
面向智能座舱的云边协同 AI Agent：端侧毫秒级车控，云端声明式 Multi-Agent 与 Skill/DAG 编排，支持 S2S 实时语音、声纹多用户、视觉与 HMI；LLM 只负责理解与规划，VAL 负责确定性安全执行。
AIMA
AI-Inference-Managed-by-AI: Go binary for managing AI inference on edge devices
OmniAgent
OmniAgent — A self-hosted AI agent that remembers, reasons, uses tools, executes Python, searches the web, and runs across Discord and Telegram.
VoxWeft
On-device simultaneous interpretation on Apple Silicon — VoxCPM2 on MLX at the core, streaming TTS in ~170 ms, voice clone, any-pair translation without a pivot. Nothing leaves th…
OrbitMCP
Edge-Native Model Context Protocol (MCP) desktop control plane & autonomous tool dispatcher with local Ollama inference and live OS telemetry.
Erlang AI Vision Fullstack
Qwen-powered agent cameras you configure in plain language - ESP32 edge detection, laptop Qwen triage, Qwen Cloud verification, Flutter console. Track 5 EdgeAgent, Qwen Cloud Glob…
Effero
Effero is a modular runtime for building agentic AI systems.
Awesome VibeCoding
🪄 精选 Vibe Coding 开源项目合集：283 个项目，12 个分类，含 AI 硬件 / 边缘 AI / 机器人。Star ≥ 100，按分类与 Star 数排序。
OrbitMCP
Edge-Native Model Context Protocol (MCP) desktop control plane & autonomous tool dispatcher with local Ollama inference and live OS telemetry.
Tiny Agent
Tiny header-only C++20 AI agent framework for edge and embedded: DeepAgent sub-agents, middleware, MCP, SSE streaming, RAG vector stores (Qdrant, Weaviate, Milvus, Redis, Chroma),…
Flashpit Agent
智能座舱 Multi-Agent 系统：端云协同 + 多领域 Agent + 快慢双系统；LLM 只做理解与规划，确定性系统执行车控。
ESP32 LLM Agent Bridge
Bridge between LLM AI Agents and ESP32 IoT devices using lightweight UART protocol. Inspired by Device Context Protocol (DCP). Built for edge AI applications.
Axelera Voyager Local Assistant
Local AI assistant for the Axelera Voyager SDK and Metis AIPU — semantic RAG over the public Axelera sources + workflow skills, via MCP. No account, no cloud.
MATHIR
Memory-Augmented Tensor Hybrid with Intelligent Routing
SmartHaus
Agentic-on-the-Edge smart home implementation w/Microsoft Agent Framework & Model Context Protocol
Molla
Local inference server in pure Mojo. Speaks OpenAI, Anthropic, and MCP. Models are OCI artifacts. Same source runs on CPU, NVIDIA, AMD, and Apple GPUs. Apache-2.0 all the way down.
Brain Server
Local-first memory server for AI agents. Hybrid recall (vector + full-text) over SQLite, knowledge graph, MCP server, human-approved writes, tamper-evident audit chain, UMP 1.0 L3…
Cf MCP Template
Production MCP (Model Context Protocol) server on Cloudflare Workers. JSON-RPC 2.0, bearer auth, drop-in for Claude Desktop / Cursor. Companion to setkernel.com/blog/mcp-servers-i…
Moa
Cloudflare Workers AI 上的 Mixture-of-Agents 服务——多模型组合逼近前沿模型能力
Nanos
Lightweight, process-isolated WebAssembly micro-runtime for sandboxed AI agents with native GPU (Metal & CUDA) offload
Comstar
Always-on embodied AI terminal for the home. A Raspberry Pi that sees you, knows who you are, and answers out loud through a lip-synced 3D avatar. Fully self-hosted, no cloud.
Edgemesh
Cross-OS federated gateway unifying every OpenAI-compatible inference backend (Cognis fleet, Ollama, llama.cpp, vLLM) behind one /v1 endpoint
White Papers Comstar Hospital
A hospital already knows where the wheelchair is. Nobody can reach that answer at the point of work. White paper on addressable edge intelligence in healthcare: architecture, adop…
Claude Stwinbox Diagnostics
AI-powered predictive maintenance & vibration fault diagnosis — bridging STEVAL-STWINBX1 IoT edge sensors and Claude via Model Context Protocol (MCP)
Lymerorium Local LLM Debate
Self-hosted heterogeneous LLM debate engine - Gemma on Jetson edge + Qwen + Llama argue in parallel, confidence-weighted voting. +40pp MMLU vs single-model baseline.
Machine Vision Module
Локальный модуль машинного зрения: Динамический 3D scene-graph каждый кадр, MCP-сервер, $0/CPU/privat
Edge MCP Caller
270M specialist baking MCP tool knowledge into weights: 99.5% accuracy, 32x fewer prompt tokens