nanbingxyz/5ire

5ire is a cross-platform desktop AI assistant, MCP client. It compatible with major service providers, supports local knowledge base and tools via model context protocol servers .

5ire – A Sleek AI Assistant & MCP Client

What it is

  • 5ire is a desktop‑style AI chat assistant that can talk to many large‑language‑model providers (OpenAI, Anthropic, Google, Mistral, etc.) and, via the Model‑Context‑Protocol (MCP), call external tools and data sources.
  • It bundles a local knowledge‑base (vector store) for Retrieval‑Augmented Generation (RAG) and a set of UI utilities such as prompt libraries, bookmarks, and analytics.

Core capabilities

Feature What you get
MCP‑powered tools Connect the assistant to file‑system access, system info, databases, remote APIs, etc., through MCP servers – a standardized “USB‑C” style plug‑in layer for AI.
Local Knowledge Base Uses the bge‑m3 multilingual embedding model to ingest docx, xlsx, pptx, pdf, txt, csv files, store their vectors locally, and perform RAG without sending data to the cloud.
Prompt Library Create, organize, and reuse prompts with variable placeholders.
Bookmarks & Search Save any conversation (even after the original messages are deleted) and keyword‑search across all chats.
Usage Analytics Tracks API calls and spend so you can monitor costs per model/provider.
One‑click server install A script that can be embedded in a website to spin up a ready‑to‑use MCP server for your own tools.

Technology stack

  • Frontend / client: Electron‑based UI (implied by native dependencies and packaging notes).
  • Backend: Python runtime (requires uv as the package manager) and a Node.js bridge for MCP server communication.
  • Embedding model: bge‑m3 (sentence‑transformers style multilingual encoder).
  • MCP: Open protocol for exposing tools to LLMs; the repo also maintains a marketplace (mcpsvr).
  • Supported LLM providers: OpenAI, Azure, Anthropic, Google, Mistral, Doubao, Grok, DeepSeek, Ollama.

Getting started

  1. Install Python, Node.js, and uv (the Python package manager). These are needed for the MCP server component.
  2. Follow the step‑by‑step instructions in INSTALLATION.md to set up the client and optional tool support.
  3. For developers, DEVELOPMENT.md explains how to run the code locally and build extensions.
  4. Optional: use the One‑Click Server Installation Integration Guide to embed a ready‑made MCP server on your site.

Community & contribution

  • Discord: https://discord.gg/ADfBTGd5jd – fast help, feature discussion, co‑building.
  • GitHub: PRs are welcomed; the repo shows recent commit activity and closed‑issue stats.
  • Marketplace: The companion mcpsvr repo hosts a community‑driven directory of MCP servers you can browse or contribute to.
  • Funding: The author lists a Buy‑Me‑A‑Coffee link for donations.

Who might use it

  • Developers who want a plug‑and‑play UI to experiment with multiple LLM APIs.
  • Teams needing a local RAG store for proprietary documents.
  • Anyone looking to extend an AI assistant with custom tools via a standard protocol.

All details are taken directly from the repository’s README; no additional features are inferred.

Related

  • Project
    BuilderIO/agent-native

    Agent‑Native is an open‑source TypeScript framework that lets you write actions once and use them both as tools for LLM‑driven agents and as regular UI calls. It provides shared actions, data, and state, a PostgreSQL backend, authentication, automations, and UI surfaces (chat, team workspaces, etc.) to build full‑stack agentic applications such as design assistants, email managers, and analytics bots.

  • Project
    wenet-e2e/wenet

    A production-oriented end-to-end speech recognition toolkit that provides full-stack solutions for streaming and non-streaming speech-to-text.

  • Project
    harbor-framework/harbor

    Harbor is a Python framework for running and scaling benchmarks of AI agents and language models. Installable via `pip`/`uv`, it provides a CLI (`harbor run`) that lets you specify a dataset (e.g., Terminal‑Bench‑2.0), an agent (Claude‑Code, OpenHands, etc.), and a model, then executes the benchmark locally or on cloud providers (Daytona, Modal, etc.) with configurable parallelism. It also supports creating custom benchmarks and generating RL roll‑outs.

  • Project
    remsky/Kokoro-FastAPI

    A Dockerized FastAPI wrapper for the Kokoro-82M TTS model that provides an OpenAI-compatible API for high-quality, multi-language speech generation.