# kunchenguid/lavish-axi > A human-agent collaboration tool for HTML artifacts: it opens agent-generated HTML in a local browser so you can pinpoint elements and text, edit Mermaid diagrams, and send feedback to the agent. Runs as a CLI and installs as an agent skill with no setup. - Magnitude: 1.8 out of 10 — Steady - Stars: 4,326 total · +6 stars measured 2026-10-27, 00:39–10:12 UTC, ≈ 16 by evening - Star trust: star growth looks organic - Category: AI agents · Language: JavaScript · License: MIT · Created: 2026-05-11 · Last push: 2026-10-26 - GitHub: https://github.com/kunchenguid/lavish-axi · Page: https://gitnova.dev/en/r/kunchenguid/lavish-axi ## Useful for - Review an agent-generated HTML plan or design and leave pinpoint comments - Edit a Mermaid diagram authored by the agent and send changes back - Install the lavish skill in Claude Code via npx skills add and invoke it with /lavish ## Why it’s here - Star-counter measurements on 2026-10-27 (UTC), 00:39–10:12: 4320 → 4326 stars (+6). This is the change over that interval. - Estimated end-of-day forecast: about +16 stars, using observed gains and the previous day. ## 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: 397 - Issues and pull requests: 463 - Watchers: 15 - Average over the last week: 15 per day - Usual pace: 18 per day - Latest release: lavish-axi-v0.1.93 (2026-10-25) ## Stars per day, last 30 days (oldest → newest, today is partial) 2026-10-04 … 2026-11-02: 10, 15, 11, 21, 12, 15, 16, 10, 13, 14, 35, 25, 23, 9, 14, 27, 20, 22, 15, 14, 13, 7, 19, 2, None, None, None, None, None, None ## Magnitude by day, last 14 days 09-26 1.6, 09-27 1.5, 10-16 2.0, 10-17 2.1, 10-18 1.5, 10-19 1.9, 10-20 2.1, 10-21 2.0, 10-22 1.9, 10-23 1.6, 10-24 1.7, 10-25 1.5, 10-26 1.6, 10-27 1.9 --- 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 2026-10-27 10:19 UTC, updated every 30 minutes.