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
Pipelinely 讓您的 Claude Code 代理程式通過單一管線執行——從規劃到合併——讓您不必守護終端分頁。本機執行於 macOS。
AI 翻譯
Pipelinely runs your Claude Code agents through one pipeline — from planning to merge — so you stop babysitting terminal tabs. Runs locally on macOS.
開發工具TypeScript · CSSGitHub @ayaniv上線中營運者未確認
試用過了嗎? 點一下就好,不需要登入。
個人 GitHub 帳號下公開儲存庫的擁有者可以登入並驗證所有權,自行管理介紹,無需管理員核准。
登入並產生驗證檔案,在 30 分鐘內將其提交至此儲存庫的預設分支。其他分支或分叉儲存庫中的檔案無效。然後在下方檢查檔案,即可無需管理員核准直接管理專案。請保留檔案以維持管理權限。
如需登入,將前往登入頁面。登入後請回到此處,再次點擊所選的驗證按鈕。
在專案資料夾中執行 /nomorevibe verify,即可驗證所有權並自行管理介紹。
一分鐘完成驗證您的 Claude Code 代理程式,通過單一管線執行。
AI 翻譯
Your Claude Code agents, running through one pipeline.
取自儲存庫 README
正在載入完整 README。 以下為已儲存的摘錄。
A local dashboard + workflow orchestrator for running a fleet of Claude Code
worker agents through a real staged pipeline — Planning → Plan Review → Dev →
QA → QA fixes → Code Review → Comment fixes → Merge — each stage its own
isolated worker in its own git worktree and its own tmux session/iTerm2 tab.
The dashboard shows every task's live stage, context %, token cost, and a
one-click jump back to its terminal; the orchestrator never does task work
itself, it only dispatches.檢視完整 README ↗目前無法載入完整 README。請透過原文連結閱讀。 以下為已儲存的摘錄。
A local dashboard + workflow orchestrator for running a fleet of Claude Code
worker agents through a real staged pipeline — Planning → Plan Review → Dev →
QA → QA fixes → Code Review → Comment fixes → Merge — each stage its own
isolated worker in its own git worktree and its own tmux session/iTerm2 tab.
The dashboard shows every task's live stage, context %, token cost, and a
one-click jump back to its terminal; the orchestrator never does task work
itself, it only dispatches.檢視完整 README ↗