Ross ROSS = Recommend OSS · open-source software intelligence for agents

SimonSchubert/Kai

OpenClaw alternative in your pocket observed · 2026-08-28

github.com/SimonSchubert/Kai · homepage · Kotlin · Apache-2.0 (permissive) observed · 2026-08-28

Health v2 · maintenance only

83/100

  • Activity 99
  • Release rhythm 84
  • Longevity 43
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 1
  • age_days: 612
  • days_rel: 31
  • days_push: 7
  • n_releases_24m: 90

Full methodology

Adoption not part of the score

1191 stars · 164 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Kai 9000 is an open-source, cross-platform AI assistant built with Kotlin Multiplatform that runs on Android, iOS, Windows, Mac, Linux, and Web. It offers persistent memory, autonomous background heartbeats, tool execution, MCP server support, and fully offline on-device inference with Gemma 4.

Use cases

  • run a private AI assistant fully offline on my phone
  • chat with an AI that remembers facts across conversations
  • use an open-source OpenClaw alternative on Android and iOS
  • connect an assistant to MCP servers and tools like web search and calendar
  • run Gemma locally on Android without an API key
  • configure multiple LLM providers with automatic fallback
  • let an AI assistant run scheduled background self-checks and notify me

When to choose

  • you want a privacy-focused, local-first assistant with encrypted on-device storage
  • you need one assistant app across mobile, desktop, and web
  • you want on-device inference with no API key or cost
  • you need tool execution, MCP support, and persistent memory in a mobile assistant

When to avoid

  • you need a server-side or team-deployed assistant with shared accounts
  • you require fine-grained agent orchestration or custom agent pipelines beyond a personal assistant
  • you need provider features not covered by OpenAI-compatible or native Gemini APIs

Facets

application · maturity active

chatbot llm-inference agent-framework mcp chat-interface tts cryptography artificial-intelligence large-language-models chatbots mobile-development cross-platform privacy windows cross-platform kotlin-multiplatform jetpack-compose openai-compatible on-device-inference gemma litert persistent-memory local-first openclaw-alternative ai-assistant ai-agents android ios macos linux mobile desktop web-server

3 sources

Member repositories

RepositoryRoleHealth v2
SimonSchubert/Kaimain83

For agents

markdown · JSON · MCP: product_card(name="SimonSchubert/Kai")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem