- Conduid
- Marketplace
- #local-llm
MCP servers tagged local-llm
463 live MCP servers tagged "local-llm", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with local-llm.
Plugin Bridge Ollama
Ollama local LLM bridge — run AI prompts against locally-hosted models — 5 MCP tools.
Financial MCP Poc
Business evaluation workflow PoC using MCP and local LLMs
Gemma4 Bench
MacBook Air M2 24GB 한 대로 돌리는 Claude × 로컬 LLM 하이브리드 멀티-티어 오케스트레이션 — 컨셉·벤치마크·실전 셋업
Localclaude
Run Claude Code locally on Apple Silicon - Qwen via vllm-mlx fork, web search via SearXNG MCP. One-script install. No cloud, no API keys, no rate limits.
Gophermind.com
🐹 A tiny, hackable AI coding agent for your terminal — a single Go binary pointed at your own OpenAI-compatible LLM. Safety built in, no cloud lock-in.
LLM Hub
Self-hosted hub for local & cloud LLMs. Unifies Ollama, Anthropic, Google & OpenAI behind one OpenAI-compatible gateway. Features an MCP server generator, Anthropic skills manager…
Xenia Plugins
Autonomous AI dev for VS Code and IntelliJ. Queue tasks for Claude, GPT-4o, Gemini, Mistral or local models. Codes while you sleep.
Obsidian Vault Librarian
Librarian: AI Agent living in Obsidian. Support PC and Mobile. Browse your vault and internet.
Llama.cpp Workbench
A reusable local LLM environment built with llama.cpp and MCP, featuring custom tools, web search, and sandboxed filesystem access.
Android Lite
MCP server to drive Android from the UI tree only (no screenshots, no vision) — ~100-250 tokens per screen. Built on google/artemis.
Sherpa MCP
A Claude Code plugin that offloads the heavy lifting — reading, searching, and batch-editing code — to your local LLM. Claude does the thinking; your local model does the grunt wo…
Beamxng
🛸 BeamXNG - Ultra-lightweight Rust gateway for SearXNG public instances
Space Weather Observatory
Follow the Sun: a local, source-grounded desktop dashboard for NOAA space weather, with plain-language reports from a local AI model (Ollama + MCP).
Opencode Enhanced
A fork of opencode adding a tokens/second indicator, a tool-free chat agent mode, and Playwright browser automation.
Myrmion Graphrag
Servidor MCP que expone una base GraphRAG local (LightRAG + Ollama) a Claude Code en VS Code. Privado, sin nube, sin claves de API.
Qwen Local Guide
Interactive, 100% local build guide: run Qwen on a Mac mini M4 (16GB) → RAG + multi-agent shared memory. One self-contained, offline HTML file.
Hermes Local Agent Lanes
Safe local-model MCP support lanes for a cloud owner agent
Network MCP Chat
Local LLM chat for network engineers — Cisco SSH + Forward Networks + Sec Ops via MCP
AI Agent Bridge
AI Agent Bridge for VS Code — local models, DeepSeek, Codex, and Claude with native tools, memory, context control, and diagnostics.
HelloSupport
Local-only multi-agent troubleshooting assistant: LangGraph agents, RAG (Chroma + reranker), MCP tools, guarded text-to-SQL, 4B vs 7B LLM benchmark on an 8 GB GPU.
Tiancode
Tiancode by ZenithAI: local-first agentic coding. Windows desktop app + CLI for Windows, macOS and Linux (GGUF local models, 14 specialists, live preview, voice, MCP).
Shuttle Stack
Local-inference layer for coding agents: your files are read by llama.cpp on your machine, not by your agent's context. MCP, rootless Podman, no egress, cited answers, measured.
Voxis Source Available
Voxis Source-Available: self-hosted, inspectable audio transcription with local AI summaries (source-available, not open source)
Messanger App
Unreal Engine UMG messenger UI built by a local AI agent through Figma and Unreal MCP bridges
Llama Gradio Ui
Local-first Gradio 6 chat UI for llama.cpp with MCP tool-calling and an optional Presidio-based privacy shield.
SCYTHE
Scythe (ctx) is a live, auto-updating codebase context engine. It maintains a local SQLite relational graph of your repository, synced dynamically on edit by AI models, guaranteei…
Anomaly AI Agent
Anomaly - a desktop AI agent built with Electron, React, Vite and TypeScript. ChatGPT-style web search with citations and a Sources panel, sub-agents, skills, 15+ tools, MCP suppo…
Toolbelt Selfhost
Reference deployments for self-hosting Toolbelt — the whole stack on your own hardware, one command.
Astro Miner E4b
Asteroid mining HTML5 space game — generated by Gemma 4 E4B (4B) + Serena MCP on Jetson Orin Nano. Newtonian physics, 3 ore types, mining laser, refining, 5 upgrades. 1,379 lines,…
Jichi
自治（じち） jichi means autonomy / self-government, and a rarer, literary homophone 自知（じち） reads as self-knowledge. jichi is a complete AI coding agent in C, conforming to the C89 (ANS…
Flacli
Get music onto disk from any agent: playlists and named albums via MusicBrainz, your library, and Soulseek through your own Nicotine+. CLI + MCP.
Local LLM App
Windows 向けローカル LLM アプリ。WinUI 3 で llama.cpp、Open WebUI、チャット、画像入力、ファイル操作、Playwright MCP によるバックグラウンド検索を統合。
ShadowCode
Linux desktop coding agent: one picker for your Codex, Claude Code, Cursor, Antigravity and Grok subscriptions, hundreds of OpenRouter models, or local GGUF models on llama.cpp.
Ollama Agent
A local-first, privacy-preserving AI agent system that uses MCP and Ollama to run all inference on your machine, providing intelligent responses and tool execution through a globa…
Houtini Lm
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.
Local Rag
This is a local rag with retrieval-augmented experience log for coding with indexed framework, reranking documents, emdedding-normalization
Roampal
Memory that learns what works.
Mostik
Free, open-source dictation for macOS that spells your code right. On-device speech recognition, a glossary from your repo, meeting recording with speakers, CLI and MCP for coding…
Multi Agent System
Production multi-agent system: LangGraph supervisor graph, MCP tool server, ChromaDB memory, SQLite observability, FastAPI — runs free on local Ollama.
Roampal
Memory that learns what works.
Codemaxxing Desktop
Native desktop app for the codemaxxing coding agent. Connect any LLM, drive a real agent loop, on macOS, Windows, and Linux.
Localmind
AI destekli yerel hafıza sistemi — MCP entegrasyonu, semantik arama, web dashboard
LMStudioClaw
Windows tray controller + local web UI that runs a call-based, LM Studio-powered agent: no model loaded at idle, load-run-unload per session/automation, with skills, custom tools,…
AETHER
AETHER — voice-driven meta-orchestrator that turns one spoken request into a fleet of self-checking AI agents
Polyglot
A coding-agent CLI that works the same way whether the model is Claude, GPT, or an open-weight model running locally.
Vellium
Local-first desktop AI workbench for roleplay, multi-character chat, long-form writing, RAG, MCP tools, plugins, and local models.
LlamaServerLauncherAvalonia
Corrallama: desktop app to run and manage llama.cpp llama-server instances - launch profiles, llama.cpp build updates, Hugging Face downloads, benchmarks and automatic parameter t…
Personal Knowledge Base MCP
A local knowledge base MCP server for **Odysseus**. It indexes folders of text documents into SQLite and lets Odie search them by keyword. It uses only the Python standard library…
AI Tools Index
A maintained index of AI developer tools: coding agents, app builders, MCP servers and agent infrastructure, with live GitHub stats.
Revitmcp
Sovereign AI+RAG for BIM. A Revit MCP proxy connecting Autodesk Revit MCP Server to AnythingLLM for local LLMs+RAG for deterministic architectural QA/QC and secure document auditi…