Daniel Saad

About

Daniel Saad works in AI engineering, based in Germany. Something with GenAI and LLMs. Public projects on GitHub include Mispher (Mispher turns speech into clean text anywhere on macOS, then goes further - dictation cleanup,…), Ripple (An on-device coding agent for your terminal, built on the Apple stack: local models with Apple MLX and an…) and Fuzzy Jev (Ask Jev typed questions about text and get calibrated probabilities back, then turn them into decisions with…), mostly written in Swift, Rust and Python.

Projects 6

• 

  Mispher

  Mispher turns speech into clean text anywhere on macOS, then goes further - dictation cleanup, rewrite-in-place, translation, and an on-device agent that plans, uses tools, and answers. No cloud, no accounts. Nothing leaves your Mac.

  github.com
• 

  Ripple

  An on-device coding agent for your terminal, built on the Apple stack: local models with Apple MLX and an Apple Container sandbox (remote models supported too).

  github.com
• 

  Fuzzy Jev

  Ask Jev typed questions about text and get calibrated probabilities back, then turn them into decisions with fuzzy rules (AND, OR, NOT, hedges, Mamdani outputs) and draw the rule base as SVG. A CLI and a Rust library (native and wasm32).

  github.com
• 

  Kino Checker

  Kino Tracker Bot is a Telegram bot that tracks the availability of movies in a selected cinema and notifies users when a movie becomes available.

  github.com
• 

  Deepagents Swift

  An inference-agnostic Deep Agents framework for Swift.

  github.com
• github.com

  Second Opinion

  A Claude Code skill that asks OpenAI Codex for an independent second opinion on technical questions, design decisions, code reviews, or debugging.