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
Open standard for persistent, self-evolving LLM agent memory (open-core, Apache-2.0).
翻譯準備中
開發工具Python · ShellGitHub @ssanvi-builds自行安裝營運者未確認
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。
安裝型專案無需部署網域也可驗證。個人儲存庫可透過 GitHub 登入驗證,組織儲存庫可使用上方的儲存庫驗證檔案。
正在載入完整 README。 以下為已儲存的摘錄。
Persistent, bi-temporal memory for LLM agents — local-first, MCP-native,
Obsidian-readable. This is what your agent's memory looks like — a markdown
file you can read in Obsidian, diff in git, and edit by hand (abridged):
That second command is the whole onboarding — vault, database, capture hooks,
observer, MCP registration, agent instructions, skills, LLM provider. It always
exits 0: steps that cannot complete degrade to a WARN line with the exact fix.
Full flags and uninstall in docs/setup.md.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。
Persistent, bi-temporal memory for LLM agents — local-first, MCP-native,
Obsidian-readable. This is what your agent's memory looks like — a markdown
file you can read in Obsidian, diff in git, and edit by hand (abridged):
That second command is the whole onboarding — vault, database, capture hooks,
observer, MCP registration, agent instructions, skills, LLM provider. It always
exits 0: steps that cannot complete degrade to a WARN line with the exact fix.
Full flags and uninstall in docs/setup.md.檢視完整 README ↗