# signerlabs/Klee

A native macOS AI chat app powered by MLX. 100% local inference on Apple Silicon, no cloud required. Built with ShipSwift.

Repository: https://github.com/signerlabs/Klee
Canonical: https://ross.abutalabs.com/products/signerlabs-klee
Homepage: https://shipswift.app
Language: Swift
License Family: other
Topics: app, klee, self-hosted, apple-silicon, llm, mcp, mlx, swift, swiftui
Last push: 2026-03-20T06:11:53+00:00

## Health v2 (maintenance only)
Score: 56/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 73, release rhythm 43, longevity 39
- inputs: {"age_days": 552, "days_push": 166, "days_rel": 167, "gap_med": null, "n_releases_24m": 1}
- 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 1762, forks 135 (observed 2026-08-28T04:05:32.691284+00:00)

## What it is
Klee is a native macOS AI chat application that runs large language models entirely on-device using Apple's MLX framework on Apple Silicon. It requires no cloud, account, or API key, and supports tool calling, vision models, and optional web search.

## Use cases
- chat with LLMs locally on my Mac without cloud
- run open-source models on Apple Silicon
- private AI assistant that keeps data on device
- AI agent that can read and write files and run shell commands
- chat with images using vision language models locally
- download and try quantized MLX models with one click

## When to choose
- you have an Apple Silicon Mac with 16GB+ RAM and want fully local LLM inference
- privacy matters and conversations must never leave your device
- you want a lightweight native app instead of Electron or Docker-based solutions
- you want built-in tool calling for files, shell, and web search

## When to avoid
- you need cloud-scale models or GPU cluster inference
- you're on Windows, Linux, or Intel Macs
- you need a server-side API or multi-user deployment
- you require a permissive open-source license for redistribution (no license is specified)

## Facets
- artifact type: application
- maturity: active
- function: llm-inference, chatbot, agent-framework, mcp, machine-learning
- domain: large-language-models, artificial-intelligence, apple-ecosystem, privacy, self-hosted
- platform: -
- tags: mlx, apple-silicon, local-inference, swiftui, on-device-llm, no-cloud, tool-calling, vision-models, ai-agents, macos, desktop, swift

## Member repositories
- signerlabs/Klee (main) score 56

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:32.691284+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 2026-08-30T03:27:02.492439+00:00, confidence not recorded.
  - readme: https://github.com/signerlabs/Klee (fetched 2026-08-28T04:05:32.691284+00:00, sha c417b27c0d23)
  - homepage: https://shipswift.app (fetched 2026-08-29T11:05:18.679391+00:00, sha 9073b7f023d8)
- Data as of 2026-08-30T08:39:29.467469+00:00.