# FigureSultanLast/roblox-ai-studio-agent > A terminal AI agent that builds Roblox places in Studio: parts, models, UI and Luau scripts, showing a place diff before each change and playtesting the result. Runs on a free local Ollama model or your own Claude/GPT/Gemini key. - Magnitude: 4.7 out of 10 — Early signal - Stars: 160 total · +41 stars measured 2026-10-31, 11:32–13:38 UTC, ≈ 64 by evening - Star trust: star growth looks organic - Category: AI agents · Language: Luau · License: MIT · Created: 2026-10-30 · Last push: 2026-10-30 - GitHub: https://github.com/FigureSultanLast/roblox-ai-studio-agent · Page: https://gitnova.dev/en/r/FigureSultanLast/roblox-ai-studio-agent ## Useful for - Generate a lobby with a spawn pad, coins and a leaderboard from a text prompt - Review the place diff before applying changes to Studio - Run a playtest and auto-fix Luau errors until Output is clean ## Why it’s here - Star-counter measurements on 2026-10-31 (UTC), 11:32–13:38: 119 → 160 stars (+41). This is the change over that interval. - Estimated end-of-day forecast: about +64 stars, using observed gains and the previous day. - The repository is 1 day old and already has 160 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet. - About 26 forks a day — people are taking the code. ## 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: 9 - Issues and pull requests: 0 - Watchers: 0 - Average over the last week: 47 per day - Usual pace: too little history (under two weeks) - Stars in the last hour (measured): 12 - Latest release: v1.8.4 (2026-10-30) ## Stars per day, last 2 days (oldest → newest, today is partial) 2026-10-30 … 2026-10-31: 30, 41 ## More in this category 1. **wangzan101/Mika** — 8.7 · Breakout · AI agents · Kotlin · +942 stars measured 2026-10-31, 00:27–13:37 UTC, ≈ 1,626 by evening Mika is an on-device AI agent for Android that carries out one-sentence requests by operating apps and the web on a hidden background screen while you keep using your phone. It uses your own model API key, with no project servers. Full card: https://gitnova.dev/en/r/wangzan101/Mika.md 2. **ccch1mneyyy/dsh-Go** — 8.6 · Breakout · AI agents · Dart · +811 stars measured 2026-10-31, 00:27–13:37 UTC, ≈ 1,516 by evening Unofficial Android client for DeepSeek Harness: runs DSH on the phone in a built-in Linux environment without root or Termux, and can also remotely control DSH on your computer. Full card: https://gitnova.dev/en/r/ccch1mneyyy/dsh-Go.md 3. **heydamir/unslop** — 8.4 · Breakout · AI agents · JavaScript · +1,309 stars measured 2026-10-31, 00:27–13:38 UTC, ≈ 2,161 by evening A Claude skill that audits and redesigns AI-generated, «vibecoded» UI screen by screen, replacing purple gradients, glows and emoji labels with a deliberate design direction. Full card: https://gitnova.dev/en/r/heydamir/unslop.md 4. **Orkas-AI/Orkas** — 8.2 · Breakout · AI agents · JavaScript · +926 stars measured 2026-10-31, 00:27–13:37 UTC, ≈ 1,508 by evening A local-first desktop app with a team of AI agents: a Commander turns a goal into to-dos and coordinates 16 built-in specialists plus external coding agents (Claude Code, Codex, etc.) within projects with scheduling and connectors. Full card: https://gitnova.dev/en/r/Orkas-AI/Orkas.md 5. **milind-soni/OpenMausBot** — 8.1 · Breakout · AI agents · TypeScript · +617 stars measured 2026-10-31, 00:27–13:37 UTC, ≈ 1,105 by evening , Full card: https://gitnova.dev/en/r/milind-soni/OpenMausBot.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 2026-10-31 13:48 UTC, updated every 30 minutes.