# Chevey339/kelivo

A Flutter LLM Chat Client. Support Mobile & Desktop.

Repository: https://github.com/Chevey339/kelivo
Canonical: https://ross.abutalabs.com/products/kelivo
Homepage: https://kelivo.psycheas.top
Language: Dart
License: AGPL-3.0
License Family: copyleft
Topics: ai, android, flutter, flutter-apps, harmonyos, ios, llm, harmony, openharmony, chatbot, chatbox
Last push: 2026-08-26T14:35:27+00:00

## Health v2 (maintenance only)
Score: 84/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 99, longevity 26
- inputs: {"age_days": 369, "days_push": 7, "days_rel": 8, "gap_med": 5, "n_releases_24m": 36}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3766, forks 406 (observed 2026-08-28T04:08:18.016985+00:00)

## What it is
Kelivo is an open-source, cross-platform LLM chat client built with Flutter that runs on Android, iOS, HarmonyOS, Windows, macOS, and Linux. It connects to multiple AI providers such as OpenAI, Anthropic, and Google Gemini, with custom assistants, multimodal input, MCP tool calling, web search integration, and text-to-speech.

## Use cases
- chat with ChatGPT, Claude, and Gemini from one app on my phone
- open source LLM chat app for Android and iOS
- AI chat client with MCP tool calling support
- use a ChatGPT-style app on HarmonyOS
- desktop chat app for OpenAI-compatible API endpoints
- talk to AI assistants with voice input and text-to-speech
- chat client that searches the web for up-to-date answers
- privacy-focused local-first chat client for multiple AI providers

## When to choose
- You want one polished cross-platform app to talk to many LLM providers (OpenAI, Anthropic, Gemini, and OpenAI-compatible endpoints) instead of switching between vendor apps
- You need MCP tool integration, web search grounding, or TTS/voice built into a mobile or desktop chat client
- You need an LLM chat app that runs on HarmonyOS/OpenHarmony, which few chat clients support

## When to avoid
- You need a library or SDK to embed chat functionality into your own application - Kelivo is an end-user application, not a development library
- You need built-in local model inference - it talks to provider APIs rather than running models itself
- You need a self-hosted shared backend, team chat server, or API gateway - this is a local-first single-user client

## Facets
- artifact type: application
- maturity: active
- function: chatbot, chat-interface, mcp, tts
- domain: artificial-intelligence, large-language-models, chatbots
- platform: windows, cross-platform
- tags: flutter, harmonyos, openharmony, llm-chat-client, multi-provider, mcp-client, web-search-integration, text-to-speech, voice-input, multimodal-input, material-you, local-first, openai, anthropic, google-gemini, chatbox, android, ios, macos, linux, mobile, desktop

## Member repositories
- Chevey339/kelivo (main) score 84

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:18.016985+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 2026-08-29T18:28:35.721712+00:00, confidence not recorded.
  - readme: https://github.com/Chevey339/kelivo (fetched 2026-08-28T04:08:18.016985+00:00, sha 2891910205bd)
  - homepage: https://kelivo.psycheas.top (fetched 2026-08-29T09:22:41.739450+00:00, sha 0a3fa7e2fc60)
  - site_page: https://kelivo.psycheas.top/docs/getting-started/quick-start (fetched 2026-08-29T09:22:41.748403+00:00, sha dafbccfe98f8)
- Data as of 2026-08-30T08:39:29.467469+00:00.