AI tool
kimi-k3-in-c
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
- Rank
- #1 of 2,808
- Stars
- 1,222★ +232/wk
- On radar
- since 2026-08-03
Momentum
rate of rise, not size · recomputes hourly
91.0
24h· new7d· new
Collecting daily history; the trend chart appears after 3 days on the radar
Why it's ranked
kimi-k3-in-c is a tool in the AI builder stack ranked #1 of 2,808 on the Cresting momentum radar, with a score of 91.0. It has 1,222 GitHub stars, +232 in the last 7 days, and has been tracked since 2026-08-03.
Every score decomposes into published factors, the same math for every tool, paid or not. Read the methodology →
| Velocity (weighted, cohort-normalized) | 0.977 |
| Recency boost | 0.829 |
| Signal decay | 0.999 |
| Corroboration | 1.000 |
| Quality gate | 1.000 |
Raw signals (30 days)
github · forks+38 in window · 188 latest · 2 snapshots
github · stars+232 in window · 1,222 latest · 2 snapshots
Related tools
- codex-vision-proxy让纯文本模型在 Codex 中无障碍调用内置看图工具（view_image）的方案，附为纯文本 LLM 设计的视觉工具包&skill ｜ Let text-only models call Codex's built-in view_image seamlessly, plus a vision toolkit&skill designed for text-only LLMs.#4 · 252★
- vibe-astockA 股短线复盘看板：涨停池·连板梯队·龙虎榜·板块资金一屏看完，赚钱效应/晋级率/梯队断层/情绪周期等派生指标纯计算直出（不经过 AI），AI 只把数据串成能读的盘面研判。全本地运行，可用 Claude/Codex 订阅免 API key。| A-share short-term daily-review dashboard: derived sentiment metrics computed locally, AI only writes the narrative. No API key needed.#9 · 121★
- ratchetYour agent reads the rules. This checks whether it followed them.#10 · 424★
- cindyConsider it done. The open-source AI agent that works out of the box · 想到，就能做到。开源、开箱即用的 AI Agent。#14 · 1,631★
- pinvou-agentOpen-source desktop AI agent for tools, files, knowledge, workflows, and real deliverables.#16 · 270★