Epiphany

io.github.GATSV-tech由 GitHub 帳號 GATSV-tech 發布v0.5.0更新於 Oct 25, 2026

One private, local memory your AI tools share. Cross-model, on-device, never lose a session.

已驗證STDIO僅桌面知識與記憶AI 與機器學習

概覽

AI 產生的概覽

Epiphany 是本地私有記憶伺服器,讓 AI 助理在本機不同 AI 工具之間共用並取用上下文記憶。

可以做什麼
從本機共用記憶圖譜召回已存的想法及其推理依據,讓助理接續先前工作階段或其他 AI 工具的上下文。儲存新記憶,並在想法之間建立明確的推理連結,例如 because、builds_on。透過背景監看器讀取已連接工具的工作階段紀錄,自動歸檔已結束甚至中斷的工作階段。透過儀表板與互動式圖譜檢視、搜尋和整理記憶。將伺服器接入支援的 AI 工具,並安裝常駐規則,讓代理主動使用記憶。
適用情境
當你同時使用多個 AI 工具、反覆說明相同背景,或希望對話結束後仍保留推理過程時適用。也適合希望記憶完全留在本機、不依賴雲端帳號的使用者。
執行需求
在桌上型電腦以本機程序執行,需要 Node.js 18 以上版本,可透過 npm 套件安裝或從原始碼建置。記憶存放在使用者家目錄下的 SQLite 檔案。不需帳號、API 金鑰或雲端服務;選用的 weave 指令會使用你自己的 LLM 金鑰。
安裝前請注意
背景監看器會讀取 AI 工具已寫入磁碟的工作階段紀錄並歸檔到本機記憶,請先確認這些日誌的內容。記憶資料庫是磁碟上的普通檔案,備份或刪除由你負責。選用的 weave 指令會使用你自己的 LLM 金鑰。接入工具會修改該工具的設定並加入常駐規則。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Epiphany,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照 儲存庫 中的啟動說明。

README

Epiphany

One private, local memory your AI tools share.

Every AI you use forgets you the moment the chat ends. You re-explain the same context over and over, and when a session dies, the reasoning behind it is gone for good. Epiphany fixes that. It's a single memory that lives on your machine, that Claude, Grok, Gemini, and more all read from and write to, so what you tell one, the others already know.

  • Local-first. Your brain is a file on your disk. Nothing leaves the machine. No account, no cloud, no company owns your memory.
  • Cross-model. One shared memory across Claude (Desktop + Code), Grok, Gemini, Cursor, Antigravity, Warp, Hermes, and Perplexity. Tell Grok something, ask Claude about it.
  • Real memory, not bullet points. Thoughts carry their reasoning and connect into a graph, so recall returns why something is true and what it followed from, not a lone fact. Ask a follow-up and it holds the thread.
  • Never lose a session. A background watcher reads the transcripts your tools already write to disk and files every session into the brain in near-real-time, even ones that crashed before anything was saved.

How it works

Epiphany is a local MCP server plus a tiny CLI.

  1. It runs a small server on your machine that exposes two tools to any AI client: recall and remember.
  2. epiphany connect <tool> wires that server into each AI tool, in the tool's own config format, and installs a standing rule so the agent reaches for your memory on its own.
  3. Memories are embedded on-device (a local model, nothing sent anywhere) and stored in SQLite. Agents wire explicit reasoning connections between thoughts (because, builds_on, part_of, ...), and recall walks that graph to reconstruct the whole thought-string.
  4. A background watcher sees your tools' session logs the moment they change and sweeps them into the brain, so nothing is ever lost.

The intelligence stays in the models you already use. The brain itself is a fast, private librarian: it holds, connects, and recalls. It never phones home.


Quickstart

Requires Node 18+.

bash
npm install -g epiphany-mcp   # puts the `epiphany` command on your PATH

Or build from source:

bash
git clone https://github.com/GATSV-tech/epiphany.gitcd epiphanynpm installnpm run buildnpm link

Wire it into the tools you use, then fully restart each one:

bash
epiphany connect claude-codeepiphany connect grokepiphany connect geminiepiphany list          # see all supported tools

Turn on the background "never lose a session" sweep:

bash
epiphany schedule

That's it. Now talk to any connected AI. It will recall what you've told the others and save what's worth keeping, on its own.

Run epiphany with no arguments any time to open the dashboard and look inside your brain.


Supported tools

ToolConnectorStanding rule
Claude Code (every terminal)autoauto
Grok CLIautoauto
Gemini CLIautoauto
Antigravity (Google IDE)autoshared with Gemini
Claude Desktopautoguided (account setting)
Cursorautoguided (app setting)
Warp (terminal, Agent Mode)autoguided (app setting)
Hermes (Nous Research agent)autoguided (instructions)
Perplexity (Mac app)guidedguided (instructions)

Commands

epiphany connect <tool>   wire Epiphany into an AI tool (connector + rule)epiphany rule <tool>      update just the standing rule for a toolepiphany list             show supported toolsepiphany dash             open the interactive dashboard (browse, search, curate)epiphany graph            see your whole brain as an interactive visual graphepiphany weave            wire the reasoning connections between related memories (optional; uses your LLM key)epiphany status           show brain size, connected tools, and auto-capture stateepiphany ingest           sweep session logs into the brain now (one-shot)epiphany watch            run the near-real-time watcher in the foregroundepiphany schedule         install the background watcher (captures sessions as they happen)

Your brain lives at ~/.epiphany/brain.db. It's yours. Back it up, inspect it, delete it, it's just SQLite.


Roadmap

Epiphany's core, local cross-model memory with reasoning graphs and automatic capture, works today. Next:

  • More session sources for the ingestor (Claude Code, Cursor transcripts).
  • Reconciliation. When a fact changes, the brain flags the conflict and you confirm the update, so memory self-corrects instead of piling up contradictions.
  • Cloud bridge. An optional relay so cloud-only surfaces (ChatGPT on the web, wearables) can reach your local brain.
  • Desktop app. A download-and-run shell for people who don't live in a terminal.

Contributions and ideas welcome.


License

MIT.

來源:README.md,提交 eecacea

工具

0
SourceWeft 尚未在沙箱中啟動過該軟體包,因此其工具未知。

版本歷史

1
  1. v0.5.0最新Sep 16, 2026

評分

已滿足適用檢查項的 50%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通25 分

    請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。

  • 已宣告認證方式10 分

    請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。

  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分