AI agent
mi
self-extending sandboxed agentic harness. a loop, two tools and an llm
- Rank
- #1464 of 2,451
- Stars
- 100★ +2/wk
- On radar
- since 2026-07-07
Momentum
rate of rise, not size · recomputes hourly
39.9
24h· new7d· new
Hover the chart for daily values
Why it's ranked
mi is an AI agent ranked #1464 of 2,451 on the Cresting momentum radar, with a score of 39.9. It has 100 GitHub stars, +2 in the last 7 days, and has been tracked since 2026-07-07.
Every score decomposes into published factors, the same math for every tool, paid or not. Read the methodology →
| Velocity (weighted, cohort-normalized) | 0.672 |
| Recency boost | 0.002 |
| Signal decay | 0.988 |
| Corroboration | 1.000 |
| Quality gate | 1.000 |
Raw signals (30 days)
github · forks+1 in window · 10 latest · 6 snapshots
github · stars+2 in window · 100 latest · 6 snapshots
Related ai agents
- speak-human-tw「說人話」：繁體中文的去 AI 味改寫 skill。抓 38 種 AI 寫作痕跡，順手校正中國用語與半形標點，給 Claude Code / Codex / Cursor 用。#1 · 303★
- pilotfishMulti-model orchestration layer for Claude Code — the frontier model plans, cheaper models execute, verification guards quality. One-prompt install.#2 · 365★
- guizang-material-illustration归藏的材质插画 skill：生成带字解释图、图表美化和参考辅助配图。#3 · 569★
- 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.#4 · 244★
- motion-anything✨ The agentic motion layer — an open-source, chat-native motion engine. Describe the feeling; your AI ships the animation.#5 · 400★