# 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 .

Repository: https://github.com/nanbingxyz/5ire
Canonical: https://ross.abutalabs.com/products/5ire
Homepage: https://5ire.app
Language: TypeScript
License: NOASSERTION
License Family: other
Topics: knowledge-base, llms, model-context-protocol, mcp-client, mcp
Last push: 2026-07-15T10:23:01+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 92, release rhythm 75, longevity 69
- inputs: {"age_days": 970, "days_push": 49, "days_rel": 168, "gap_med": 10.0, "n_releases_24m": 35}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5346, forks 425 (observed 2026-08-28T04:09:15.897036+00:00)

## What it is
5ire is a cross-platform desktop AI assistant and MCP (Model Context Protocol) client that connects to major LLM providers like OpenAI, Anthropic, Google, and Ollama. It supports tools via MCP servers, a local knowledge base with RAG using the bge-m3 embedding model, prompt libraries, and API usage analytics.

## Use cases
- chat with multiple llm providers from one desktop app
- connect ai tools via mcp servers
- build a local knowledge base from pdf and docx files
- run retrieval-augmented generation locally
- track llm api spending and usage
- organize and reuse prompts
- use local models with ollama

## When to choose
- you want a free desktop chat client that works with many LLM providers
- you need MCP tool support without writing code
- you want local RAG over your documents with privacy
- you want to track API costs across providers

## When to avoid
- you need a fully open-source license (license is non-standard)
- you need a web-based or team-hosted assistant
- you only want a simple CLI for LLM calls

## Facets
- artifact type: application
- maturity: active
- function: chatbot, rag, mcp, agent-framework, llm-inference
- domain: artificial-intelligence, large-language-models, chatbots, cross-platform
- platform: windows, cross-platform
- tags: mcp-client, desktop-ai-assistant, local-knowledge-base, multi-provider, prompt-library, usage-analytics, ai-agents, retrieval-augmented-generation, macos, linux, desktop

## Member repositories
- nanbingxyz/5ire (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:15.897036+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:58:48.714824+00:00, confidence not recorded.
  - readme: https://github.com/nanbingxyz/5ire (fetched 2026-08-28T04:09:15.897036+00:00, sha 24446befd105)
  - homepage: https://5ire.app (fetched 2026-08-29T08:53:31.422231+00:00, sha 747f4ededf82)
  - site_page: https://5ire.app/docs (fetched 2026-08-29T08:53:31.431328+00:00, sha 889f5ae5a5cd)
- Data as of 2026-08-30T08:39:29.467469+00:00.