ML Application · Swift

RLeon

Local-first macOS app: on-device speech & Vision OCR, local Ollama chat, and native tool calling (RLeon).

Yahya Efe Kuruçay@efekurucay · Atlas 74.0 · #2= builder

View on GitHub4 Open Yahya Efe Kuruçay's Atlas

What it is

RLeon is a macOS application that integrates on-device speech recognition, Vision-based OCR, and local LLMs via Ollama with a tool calling system to enable voice-driven dictation, screen text extraction, and automated macOS actions.

computer-vision
llm
local-first
macos
ollama
open-source
speech-recognition
swift
swiftui
tool-calling

Scored at7bd29fa12 Nov 2026Changes since

Merit describes the code at this commit. Later pushes count once the owner rescans. How merit is scored

Where it counts

Machine Learning90%
NLP & LLMs90%
Computer Vision70%
AI Agents50%
Data Science10%
MLOps10%

How much of the project is about each field, as scoring counts it. It ranks in the field it is most about.

What the judge found

Read from the project's code at its scored commit.

Strengths3

Integrates multiple on-device AI capabilities (speech recognition, OCR) with local LLM access via Ollama into a unified macOS application.
Implements a secure tool calling system that allows the LLM to perform sensitive macOS actions (e.g., terminal commands, cross-app typing) with user-controlled permissions and confirmation prompts.
Provides a polished, local-first user interface with menu bar access and FN push-to-talk interaction, emphasizing privacy and offline operation.

Limitations

The owner keeps this project's limitations private.

Around it on the Machine Learning board

Whole board

RankProjectBuilderFieldMerit