AI tool
Subtext
To know what models don't say out loud.
- Rank
- #111 of 2,420
- Stars
- 165★ +1/wk
- On radar
- since 2026-07-10
Momentum
rate of rise, not size · recomputes hourly
58.1
24h· new7d· new
Collecting daily history; the trend chart appears after 3 days on the radar
Why it's ranked
Subtext is a tool in the AI builder stack ranked #111 of 2,420 on the Cresting momentum radar, with a score of 58.1. It has 165 GitHub stars, +1 in the last 7 days, and has been tracked since 2026-07-10.
Every score decomposes into published factors, the same math for every tool, paid or not. Read the methodology →
| Velocity (weighted, cohort-normalized) | 0.647 |
| Recency boost | 0.746 |
| Signal decay | 0.999 |
| Corroboration | 1.000 |
| Quality gate | 1.000 |
Raw signals (30 days)
github · forks+0 in window · 19 latest · 2 snapshots
github · stars+1 in window · 165 latest · 2 snapshots
Related tools
- fable-methodThe Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.#2 · 159★
- FableCutZero-dependency browser video editor that AI agents can drive — JSON timeline, MCP + REST, live-reloading UI#3 · 304★
- Vibe-ResearchVibe-Research: Your Personal Trading Research Agent · A股/美股/港股 的个人投研 Agent：每日复盘、资讯雷达、个股数据、板块中心、我的持仓、研究记录。Vibe-Research 把数据和功能配齐，由你自己的 AI 驱动投资研究。#6 · 667★
- openscienceThe open-source AI workbench for scientific research#7 · 2,075★
- TalosGPU worker client for the Talos network. Pairs with your Talos account, serves open-model inference jobs over a WebSocket, and reports uptime for payouts.#12 · 929★