# parthh01/sphinx > A Git hook that asks you to predict what your change will do before pushing to a protected branch, explaining mistakes. Helps developers keep understanding of code when working with AI agents. - Magnitude: 6.1 out of 10 — Early signal - Stars: 109 total · +3 stars measured 2026-10-19, 00:06–01:29 UTC, ≈ 92 by evening - Star trust: star growth looks organic - Category: Developer tools · Language: JavaScript · License: MIT · Created: 2026-10-14 · Last push: 2026-10-19 - GitHub: https://github.com/parthh01/sphinx · Homepage: https://sphinx-six-theta.vercel.app · Page: https://gitnova.dev/en/r/parthh01/sphinx ## Useful for - Check understanding of changes before pushing to a protected branch - Configure Sphinx for a specific repository via sphinx init - Diagnose installation and configuration with sphinx doctor ## Why it’s here - Star-counter measurements on 2026-10-19 (UTC), 00:06–01:29: 106 → 109 stars (+3). This is the change over that interval. - Estimated end-of-day forecast: about +92 stars, using observed gains and the previous day. - The repository is 5 days old and already has 109 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet. - Top new repositories this week: #163. - Hacker News: “Show HN: Sphinx – A hook that quizzes you on your AI's code before shipping” — 241 points, 21 h ago. ## Star trust Star growth looks organic. Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer. ## Numbers - Forks: 4 - Issues and pull requests: 13 - Watchers: 0 - Average over the last week: 34 per day - Usual pace: too little history (under two weeks) - Stars in the last hour (measured): 2 ## Stars per day, last 6 days (oldest → newest, today is partial) 2026-10-14 … 2026-10-19: 0, 0, 0, 9, 100, 3 ## Hacker News - Show HN: Sphinx – A hook that quizzes you on your AI's code before shipping — 241 points, 85 comments: https://news.ycombinator.com/item?id=50137950 ## Spotted in now - Top new repositories this week: #163 ## More in this category 1. **feder-cr/git-ai** — 7.7 · Breakout · Developer tools · Go · +3 stars measured 2026-10-19, 00:05–01:29 UTC, ≈ 998 by evening An open-source implementation of a server-centric version control system designed for coding agents: always-online clients, server-side history and search, and compare-and-swap landing without a merge queue. Full card: https://gitnova.dev/en/r/feder-cr/git-ai.md 2. **storytold/figcraft** — 5.2 · Peaking · Developer tools · Rust · +8 stars measured 2026-10-19, 00:05–01:29 UTC, ≈ 136 by evening Open-source interface design tool in Rust: frames, auto layout, components, vectors, styles and prototypes in a native offline app. Compatible with .fig and Figma REST API JSON, driven from UI, CLI or MCP. Full card: https://gitnova.dev/en/r/storytold/figcraft.md 3. **MostafaXS1/artcraft-android** — 5.0 · Early signal · Developer tools · Shell · +3 stars measured 2026-10-19, 00:06–01:29 UTC, ≈ 77 by evening A shell-based builder that compiles locally signed 64-bit ARM Android APKs from the official Storytold repositories for the ArtCraft apps, with release/debug builds and metadata overrides. Full card: https://gitnova.dev/en/r/MostafaXS1/artcraft-android.md 4. **justrach/nanoui** — 4.8 · Early signal · Developer tools · Zig · Not enough measurements today A Zig framework for building desktop apps with an immediate-mode UI drawn on the GPU or with a web frontend in the system webview, compiled to a single binary. Full card: https://gitnova.dev/en/r/justrach/nanoui.md 5. **longbridge/nsh** — 4.7 · Early signal · Developer tools · Rust · +6 stars measured 2026-10-19, 00:06–01:29 UTC, ≈ 79 by evening Native Shell (NSH) renders UI written in TSX and Tailwind using each platform's native views on iOS, Android, macOS, Windows, Linux, GPUI and the web. It runs TSX modules as sandboxed, signed plugins inside an existing app or packages… Full card: https://gitnova.dev/en/r/longbridge/nsh.md --- Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score. Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast. Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself. Data as of 2026-10-19 01:39 UTC, updated every 30 minutes.