#local

HyperChat is a Chat client that strives for openness, utilizing APIs from various LLMs to achieve the best Chat experience, as well as implementing productivity tools through the MCP protocol.

Web and local search using Brave's Search API

Store and retrieve API keys and secrets locally for Claude Code. No cloud services, no .env files scattered across projects. Secrets are stored in a SQLite database on your machine and accessed via MCP tools. Supports add, get, list, search, update, and delete operations with category organization.

The official Model Context Protocol (MCP) server for https://zhook.dev, enabling AI agents to interact with your Zhook webhooks, events, and metrics. Create Hooks: Create new webhooks or MQTT hooks directly from your agent. List Hooks: Retrieve a list of your configured webhooks. Inspect Events: View recent events for a specific hook. Wait for Event: Pause execution and wait for a specific event to occur. Metrics: Access detailed metrics about your webhook performance.

Goman Live is a localization manager built for developers and content teams. We translate with AI, support the Model Context Protocol (MCP), provide URL-based access to translations, and include built-in context and prompt management for quality and consistency.

Goman Live is a localization manager built for developers and content teams. We translate with AI, support the Model Context Protocol (MCP), provide URL-based access to translations, and include built-in context and prompt management for quality and consistency.

Project description 🧠 RABEL MCP Server Recidive Active Brain Environment Layer Local-first AI memory with semantic search, graph relations, and soft pipelines. Mem0 inspired, HumoticaOS evolved. By Jasper & Root AI from HumoticaOS 💙 🚀 Quick Start # Install pip install mcp-server-rabel # For full features (vector search) pip install mcp-server-rabel[full] # Add to Claude CLI claude mcp add rabel -- python -m mcp_server_rabel # Verify claude mcp list # rabel: ✓ Connected 🤔 What is RABEL? RABEL gives AI assistants persistent memory that works 100% locally. Before RABEL: AI: "Who is Storm?" → "I don't know, you haven't told me" After RABEL: You: "Remember: Storm is Jasper's 7-year-old son" AI: *saves to RABEL* Later... You: "Who is Storm?" AI: *searches RABEL* → "Storm is Jasper's 7-year-old son!" No cloud. No API keys. No data leaving your machine. 🛠️ Available Tools Tool Description rabel_hello Test if RABEL is working rabel_add_memory Add a memory (fact, experience, knowledge) rabel_search Semantic search through memories rabel_add_relation Add graph relation (A --rel--> B) rabel_get_relations Query the knowledge graph rabel_get_guidance Get soft pipeline hints (EN/NL) rabel_next_step What should I do next? rabel_stats Memory statistics 📖 Examples Adding Memories # Remember facts rabel_add_memory(content="Jasper is the founder of HumoticaOS", scope="user") rabel_add_memory(content="TIBET handles trust and provenance", scope="team") rabel_add_memory(content="Always validate input before processing", scope="agent") Searching Memories # Semantic search - ask questions naturally rabel_search(query="Who founded HumoticaOS?") # → Returns: "Jasper is the founder of HumoticaOS" rabel_search(query="What handles trust?") # → Returns: "TIBET handles trust and provenance" Knowledge Graph # Add relations rabel_add_relation(subject="Jasper", predicate="father_of", object="Storm") rabel_add_relation(subject="TIBET", predicate="part_of", object="HumoticaOS") rabel_add_relation(subject="RABEL", predicate="part_of", object="HumoticaOS") # Query relations rabel_get_relations(subject="Jasper") # → Jasper --father_of--> Storm rabel_get_relations(predicate="part_of") # → TIBET --part_of--> HumoticaOS # → RABEL --part_of--> HumoticaOS Soft Pipelines (Bilingual!) # Get guidance in English rabel_get_guidance(intent="solve_puzzle", lang="en") # → "Puzzle: Read → Analyze → Attempt → Verify → Document" # Get guidance in Dutch rabel_get_guidance(intent="solve_puzzle", lang="nl") # → "Puzzel: Lezen → Analyseren → Proberen → Verifiëren → Documenteren" # What's next? rabel_next_step(intent="solve_puzzle", completed=["read", "analyze"]) # → Suggested next step: "attempt" 🏗️ Architecture ┌─────────────────────────────────────────────────────────────┐ │ RABEL │ │ Recidive Active Brain Environment Layer │ ├─────────────────────────────────────────────────────────────┤ │ │ │ Memory Layer → Semantic facts with embeddings │ │ Graph Layer → Relations between entities │ │ Soft Pipelines → Guidance without enforcement (EN/NL) │ │ │ │ Storage: SQLite + sqlite-vec (optional) │ │ Embeddings: Ollama nomic-embed-text (optional) │ │ │ │ 100% LOCAL - Zero cloud dependencies │ │ │ └─────────────────────────────────────────────────────────────┘ Graceful Degradation RABEL works with minimal dependencies: Feature Without extras With [full] Text memories ✅ ✅ Text search ✅ (LIKE query) ✅ (semantic) Graph relations ✅ ✅ Soft pipelines ✅ ✅ Vector search ❌ ✅ Embeddings ❌ ✅ (Ollama) 🌍 Philosophy "LOKAAL EERST - het systeem MOET werken zonder internet" (LOCAL FIRST - the system MUST work without internet) RABEL is built on the belief that: Your data stays yours - No cloud, no tracking, no API keys Soft guidance beats hard rules - Pipelines suggest, not enforce Bilingual by default - Dutch & English, more coming Graceful degradation - Works with minimal deps, better with more 🙏 Credits Inspired by: Mem0 - Thank you for the architecture insights! We took their ideas and made them: 100% local-first Bilingual (EN/NL) With soft pipelines With graph relations 🏢 Part of HumoticaOS RABEL is part of a larger ecosystem: Package Purpose Status mcp-server-tibet Trust & Provenance ✅ Available mcp-server-rabel Memory & Knowledge ✅ Available mcp-server-betti Complexity Management 🔜 Coming 📞 Contact HumoticaOS Website: humotica.com GitHub: github.com/jaspertvdm 📜 License MIT License - One love, one fAmIly 💙 Built with love in Den Dolder, Netherlands By Jasper & Root AI - December 2025

Lightweight local RAG MCP server for semantic vector search over markdown documents. Reduces token consumption by 40x. Supports Japanese and English.

Transform AI prompts with intelligent context detection, 50+ professional optimization techniques, and seamless team collaboration. Integrated with Claude Desktop, Cursor, Windsurf, and 17+ MCP clients. • **100% Local Processing** - All prompt optimization is done on your machine, ensuring complete privacy and confidentiality. • **Offline Capability** - Works without an internet connection, making it ideal for secure or air-gapped environments. • **Advanced Local Prompt Intelligence** - Sophisticated content analysis and optimization performed directly on your machine, including context-aware optimization for debugging and technical prompts. • **Cross-Platform Support** - Universal compatibility for Windows, macOS, and Linux. • **Binary Integrity Verification** - SHA256 hash validation ensures the integrity of the local server. • **Technical Parameter Preservation** - Maintains code blocks, API calls, and other technical details during optimization, including parameters like --ar and --v. • **Debugging Scenario Detection** - Context-aware optimization tailored for debugging and technical prompts.

Persistent codebase intelligence that gives agents memory across sessions.

A lightweight Model Context Protocol (MCP) server for Slack automation using cookie-based authentication.

The graph augmented, smart and local-first Personal Context Manager, or Personal Agent Memory, just works. Nowledge Mem ingests your agent’s summarized memories through its MCP tools or prompts, enabling you to enhance your memory and knowledge using a GraphRAG approach. By leveraging LLMs, embedding models, BM25, graph algorithms, and a built-in knowledge graph, Nowledge Mem makes building, searching, and exploring your personal knowledge easier than ever.

An MCP server implementation that integrates the Brave Search API, providing comprehensive search capabilities including web search, local business search, image search, video search, news search, and AI-powered summarization. This project supports both STDIO and HTTP transports, with STDIO as the default mode.

A powerful, intelligent shell assistant powered by local AI models through Ollama. Shell AI brings advanced AI capabilities directly to your terminal, enabling natural language interaction with your file system, shell commands, and development workflow.

The official local MCP server for Kintone.

MCP server for Roll Docker Stack and multi-framework development environments.

MCP server for accessing VS Code/Cursor Local History. Useful for file recovery.

Advanced Local Prompt Intelligence Engine with complete privacy and sophisticated content analysis. Features cross-platform support (Windows, macOS, Linux), binary optimization, and dual-tier processing: AI-aware rules engine + optional LLM enhancement. 100% local processing ensures complete privacy - no data transmission during optimization. Key Features: - Privacy-First: Complete local processing, no cloud dependencies - Cross-Platform: Native binaries for Windows, macOS (Intel/Apple Silicon), Linux (x64/ARM64) - Dual Optimization: Sophisticated rules engine + optional OpenAI LLM enhancement - Professional Tools: 50+ optimization techniques for technical and creative prompts - Template Management: Save, search, and reuse optimization patterns - Zero Setup: Works offline with cached license validation Perfect for developers, teams, and anyone requiring private prompt optimization without cloud dependencies.

Spring AI Playground is a self-hosted web UI that simplifies AI experimentation and testing. It provides Java developers with an intuitive interface for working with large language models (LLMs), vector databases, prompt engineering, and Model Context Protocol (MCP) integrations. Built on Spring AI, it supports leading model providers and includes comprehensive tools for testing retrieval-augmented generation (RAG) workflows and MCP integrations. The goal is to make AI more accessible to developers, helping them quickly prototype Spring AI-based applications with enhanced contextual awareness and external tool capabilities.

A MCP server which loads the man pages of tools in $PATH as resource. The goal is to provide the LLM with context of the commands on the host machine

Local LLM Server with NPU Acceleration

Minimalist examples to provide your own MCP servers to your local llm models.

MCP server powered by local documentation

Give your MCP clients the ability to speak by running local voice models

Local text-to-speech MCP server with dual engines (macOS Say + Kokoro TTS) for Claude Desktop

Lightweight MCP client that uses a local Ollama LLM to query multiple MCP servers defined in config.json

mcp server for personal use

Shinkai is a two click install AI manager (Local and Remote) that allows you to create AI agents in 5 minutes or less using a simple UI. Agents and tools are exposed as an MCP Server.

Code indexing MCP server to provide context to coding agents.

Self-hosted MCP Japanese text indexing & search—chunking+embeddings with BM25×vector rerank

The portable alternative to Cursor Rules and IDE-specific rules. Transform your project documentation into intelligent AI context using standard Markdown files that work across any MCP-compatible AI tool. Escape vendor lock-in and scattered documentation forever.

An MCP server to interact with the public and on demand API of Local Falcon. For more information check here: https://www.localfalcon.com/features/mcp

A flexible Model Context Protocol (MCP) proxy that enables discovery and execution of tools across multiple MCP servers and JavaScript functions. Enabling to have a reduced context event if you have houndreds of tools. This mcp act as wrapper of other mcps (or libraries) doing a kind of Local RAG (Retrieval Augmented Generation) to reduce the context size providing the llm with 2 methods (discover and execute) and asking the llm to be concise about discovery. The execute method is a simple proxy We extremely recommends add the configuration discoverDescriptionExtras to extends in details about the purpose of the tools and for what kind of topics the llm should use it.

为 LLM 提供了获取“当前”时间、日期、星期等信息的能力。有了它，LLM 回答“现在”、“最近”相关问题时，终于可以获得真正的“现在”——不再停留在模型训练的过去！

API service to search vectorized Cursor IDE chat history using LanceDB and Ollama

Mirror of

A Python-based client for interacting with Model Context Protocol (MCP) servers using Ollama. Features include multi-server support, dynamic model switching, tool management, and a rich terminal interface.

Mirror of

A MCP (Model Context Protocol) server implementation for SimpleLocalize.

MCP for Ansible, Terraform, LocalStack, and other IaC tools. Create and iterate IaC in LocalStack until ready to deploy live.

Claude Desktop MCP Server - Local desktop AI agent with file access and notifications

The MCP connects to the Kakao Local API (https://developers.kakao.com/docs/latest/ko/local/common).

This project build a local mcp server to fetch weather

This is a cross-platform desktop application that allows you to chat with locally hosted LLMs and enjoy features like MCP support

CLI tool to scaffold, run, and test MCP servers locally with Node.js or Python, integrated with Claude and OpenAI key injection and auto-link to Claude Desktop.

a magical desktop app that puts the power of LLMs and MCP in the hands of everyone

Local MCP Client is a cross-platform web and API interface for interacting with configurable MCP servers using natural language, powered by Ollama and any local LLM of choice, enabling structured tool execution and dynamic agent behavior.

(Demo) MCP Server to create and draw .vox models file locally

This Streamlit application provides a user interface for connecting to MCP (Model Context Protocol) servers and interacting with them using different LLM providers (OpenAI, Anthropic, Google...).

An MCP server that provides comprehensive access to the local Anytype API (v0.46.1). It allows to interact with your Anytype data, enabling features like: searching, retrieving, creating, and deleting spaces and objects (pages, notes, tasks, etc.). It also supports object export (Markdown), list/view management, and querying type/template information.

An ollama interface which provides models with MCPs

This is a sample local MCP server.

ローカルMCPサーバー（stdio）を作成するためのチュートリアルです。

MCP Proxy to Expose Local MCP Server

An mcp server designed for local-deployed deep research.

MCP server for scanning local code and localhost URLs

MCP server for using the AdsPower LocalAPI

Servidor para acessar e manipular arquivos locais usando MCP

An MCP tool that provides AI with the ability to compress and decompress local files.

This repo has my learnings on how to create an MCP-Server

local mcp server perplexity

A template repository that includes a dev container for running a local LLM and included knowledge base. Add a git repo using `git subtree` or `git submodule` and update it using an MCP Client/Server relationship i.e. `VS Code` extension like `Cline` and the `Filesystem`/`Obsidian-MCP` MCP server.

A centralized manager for Model Context Protocol (MCP) servers with dynamic server management and monitoring

Mirror of

MCP server providing semantic memory and persistent storage capabilities for Claude using ChromaDB and sentence transformers.

Run & Manage Long Processes - install, scrap, encode video, compile Search & Read & Edit files - including diff editing for speed and precision