AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
翻譯準備中
- 運作狀態
- 上線中
- 30 天上線率 100%
- 最近程式碼更新
- 10月20日
- 活躍儲存庫
- 貢獻者
- 2 人
- 分支 0
- 授權條款
- GitHub 自動辨識 · 先前收集的資料 · 收集於 10月27日
- nomorevibe 收錄
- 9月19日
- 儲存庫建立於 2026年8月
語言組成
- JavaScript 53.8%
- TypeScript 43.5%
- Shell 1.6%
- HTML 等 1.1%
更新最近 30 天 6 筆
全部- Catalog 0.30.1 — The three skills from 0.30.0 now hold to their own rulesGitHub 發布版本 ↗
- Catalog 0.30.0 — A shared key rotates without downtime, a review loop ends on a reviewed head, and a model comparison can be checkedGitHub 發布版本 ↗
- Catalog 0.29.0 — Someone from another field learns how a project works, in their own termsGitHub 發布版本 ↗
開發工具 分類的熱門專案
依最近已完成的 8 小時觀測回合間的 GitHub 星號增量排序
Agenvoy
Taiwan-built, self-hosted AI agent harness in a single Go binary — writes its own tools, sandbox-tests them, and shares them over MCP with Claude Code and Codex.
翻譯準備中
neuron-explorer
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
翻譯準備中
api-anything
Turn any website into an API your agent can call. Learns from the site's own frontend, heals itself when the site changes.
翻譯準備中