# johnbean393/Sidekick

A native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and websites on your Mac without installing any other software. Powered by llama.cpp.

Repository: https://github.com/johnbean393/Sidekick
Canonical: https://ross.abutalabs.com/products/johnbean393-sidekick
Homepage: https://johnbean393.github.io/Sidekick/
Language: Swift
License: MIT
License Family: permissive
Topics: ai, llama, llm, macos, rag, swift, swiftui, deepseek, deepseek-r1, aichat, chatbot, qwen, llama4, qwen3, agentic-ai, ai-agents, agents, deep-research, gpt-oss
Last push: 2026-05-24T05:34:09+00:00

## Health v2 (maintenance only)
Score: 69/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 84, release rhythm 60, longevity 49
- inputs: {"age_days": 693, "days_push": 101, "days_rel": 153, "gap_med": 2, "n_releases_24m": 50}
- flags: prerelease_only
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3314, forks 148 (observed 2026-08-28T04:07:56.069042+00:00)

## What it is
Sidekick is a native macOS app for chatting with local LLMs powered by a built-in llama.cpp backend, with RAG over local files, folders, and websites. It runs fully offline with a local-first privacy model, while also supporting OpenAI-compatible remote APIs.

## Use cases
- chat with a local llm on my mac without sending data to the cloud
- ask questions about my local files and folders with an ai
- build a private offline chatbot with retrieval over documents
- run gguf models like qwen locally on apple silicon
- get cited answers with references from my pdfs and websites
- organize knowledge into topic-specific ai experts

## When to choose
- you want a fully offline, privacy-focused LLM chat app on macOS
- you need RAG over local files, folders, and websites with cited references
- you prefer a native Swift/SwiftUI app with no extra dependencies to install
- you want built-in llama.cpp inference with optional OpenAI-compatible API support

## When to avoid
- you need a cross-platform or Linux/Windows solution
- your Mac lacks the memory/compute to run local models at acceptable speed
- you need heavy multi-user or server-side deployment features
- you want a cloud-hosted assistant with managed scaling

## Facets
- artifact type: application
- maturity: active
- function: rag, llm-inference, chatbot, chat-interface, search-engine
- domain: large-language-models, chatbots, privacy, artificial-intelligence
- platform: -
- tags: local-llm, llama-cpp, swiftui, offline-ai, gguf, local-first, agentic-ai, deep-research, retrieval-augmented-generation, macos, desktop

## Member repositories
- johnbean393/Sidekick (main) score 69

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:56.069042+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 2026-08-29T18:42:06.031745+00:00, confidence not recorded.
  - readme: https://github.com/johnbean393/Sidekick (fetched 2026-08-28T04:07:56.069042+00:00, sha 639d5bbdbfef)
  - homepage: https://johnbean393.github.io/Sidekick/ (fetched 2026-08-29T09:34:59.693221+00:00, sha 741d69b0f36b)
- Data as of 2026-08-30T08:39:29.467469+00:00.