# Lakr233/FlowDown

https://flowdown.ai/

Repository: https://github.com/Lakr233/FlowDown
Canonical: https://ross.abutalabs.com/products/flowdown
Language: Swift
License: AGPL-3.0
License Family: copyleft
Last push: 2026-08-31T16:19:23+00:00

## Health v2 (maintenance only)
Score: 84/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 100, release rhythm 88, longevity 42
- inputs: {"age_days": 595, "days_push": 2, "days_rel": 2, "gap_med": 1, "n_releases_24m": 146}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1192, forks 117 (observed 2026-09-01T02:13:55.462395+00:00)

## What it is
FlowDown is a native AI chat client for iPhone, iPad, and Mac built with Swift and UIKit. It connects to OpenAI-compatible APIs, self-hosted inference servers, Apple Intelligence, or on-device MLX models with a privacy-first, no-telemetry design.

## Use cases
- chat with AI models on iPhone and Mac
- connect to Ollama or LM Studio local models
- run on-device MLX inference on Apple Silicon
- use OpenAI-compatible API providers in a native client
- chat with vision and audio-capable models
- sync chat history across Apple devices via iCloud

## When to choose
- you want a fast native Apple-platforms chat UI instead of a web wrapper
- privacy matters and you want no telemetry or data collection
- you use self-hosted or OpenAI-compatible endpoints
- you want on-device inference with MLX

## When to avoid
- you need a cross-platform client for Windows, Linux, or Android
- you need team/enterprise chat management features
- you primarily use non-OpenAI-compatible model APIs

## Facets
- artifact type: application
- maturity: active
- function: chatbot, chat-interface, llm-inference, http-client
- domain: large-language-models, chatbots, apple-ecosystem, privacy
- platform: -
- tags: ai-chat-client, mlx, openai-compatible, native-app, icloud-sync, privacy-first, ios, macos, swift, apple-ecosystem

## Member repositories
- Lakr233/FlowDown (main) score 84

## Provenance
- Observed fields: from GitHub, fetched 2026-09-01T02:13:55.462395+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 2026-08-30T06:22:39.982002+00:00, confidence not recorded.
  - readme: https://github.com/Lakr233/FlowDown (fetched 2026-09-01T02:13:55.462395+00:00, sha cf3f0b1140e6)
- Data as of 2026-08-30T08:39:29.467469+00:00.