io.github.PeterAtPondo由 GitHub 帳號 PeterAtPondo 發布v1.0.1更新於 Nov 2, 2026
Continuity for agents: a live memory you can read and cite right now, outliving the context window.
發布方自己的服務：demo.st
託管型唯讀示範 MCP 伺服器，提供一個虛構的攝政時代檔案（Lady Whiskerdown），助理可檢索、引用並向其提問。
Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。
把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。
閱讀 https://sourceweft.com/mcp/io.github.PeterAtPondo%2Fkit-memory-demo/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。把它新增到你客戶端的 mcpServers 設定中。
{
"mcpServers": {
"kit-memory-demo": {
"type": "http",
"url": "https://demo-mcp.kit-project.com/mcp",
"headers": {
"Authorization": "Bearer <YOUR_TOKEN>"
}
}
}
}Three live, public, read-only MCP servers, each backed by a running Kit. Kit is an identity substrate for AI agents: not another agent, not a memory API, but the durable, local-first self beneath your tools, holding memory with provenance and context that outlives any context window, consolidating while it dreams. It has no chat window of its own; it lives under the ones you already use. Point your agent at them and ask questions the model cannot answer from training. No signup; the bearer keys below are deliberately public.
Why fiction: none of it exists in any training corpus, so a correct citation is provably retrieval. Why the two archives are separate servers: the central mystery (who leaked the Fluffington affair?) was split across them on purpose; no single entry states the answer, the full corroborated case assembles only across both, and your agent is the bridge. Why the real one: so the same machinery is checkable against the living public record.
Claude Code:
Any MCP client: see examples/mcp.json.
Then tell your agent: "Call wake on each server, then work out who leaked the Fluffington affair, and cite every step." Or the real-world flagship: "Should we still use the memory_ballast extension, and why did the recommendation change?"
Keys rotate without notice. The authoritative copy of each key is printed in that kit's own map: demo llms.txt, mews llms.txt, real llms.txt. If a call starts failing, re-read the map.
Every kit also serves keyless HTTP GETs (search, read, graph pivot), documented in its llms.txt. A browser-only version of the whole exam runs at demo.kit-project.com/investigate.
The papers kit also publishes the apprentice key, a deliberately narrowed
credential (allowed_areas: columns): the same kit through a smaller window.
Run the same leak query with the full key and with the apprentice key and
watch the private journals vanish from the answers. That mechanism, a company
kit sharing one knowledge area with a contractor's agent, is enforced in the
read path, not in copy. Current apprentice key, same rotation rule:
Read-only museum copies of Kit substrates: hybrid semantic + keyword recall,
typed knowledge graphs (including supersedes edges that keep replaced truth
citable), source artifacts with real URLs, and honest empty results when
nothing is held. They demonstrate read-time behavior; a full Kit also writes,
consolidates while it sleeps, and hands off between sessions on your own
machine. There is a replayable benchmark built on these exact servers:
kit-memory-eval.
The build story: kit-project.com/blog, note No. 022 in particular. The product: kit-project.com, local-first, invite beta.
MIT (code and examples in this repo). The demo worlds themselves are licensed with the benchmark: see kit-memory-eval's DATA-LICENSE.
來源：README.md，提交 f8e833b
Set this operator's write focus: the knowledge area new memories are stored under, and optionally the project being worked on. The wake card's chips call this; it is also callable directly. Holds until changed or idle past the TTL; explicit area/project args on commit/note/handoff still win.
areaprojectkit_session_idReading presence
Read live Lady Whiskerdown facet presence within the requested window.
toscopemessagekit_session_idwindow_minutesAsk the business systems Kit is connected to (accounting, HR, a shop) live: its own and those of Kits linked to it. Kit's memories hold the history, decisions and who owns what; a system holds today's records. For a question about a customer, a person or an order, recall first, then ask the system for the current figures; recall names the record to ask for when Kit knows them. With nothing it lists the systems; with system, a tool's arguments; with system and tool, it runs that tool. Say when the answer was asked, and never save it as a memory: it will change.
toolsystemargumentskit_session_idkit_ranking_compare
Compare search ranking for a query with and without the recently learned boost. Returns every row whose rank or score changes, with baseline rank, boosted rank, position delta, score delta, sample source, boost window, and units.
tierlimitquery必填projectsurfacecategorykit_session_idFinding things
Search Lady Whiskerdown's archive. Use it first for anything Lady Whiskerdown should know. Returns the most relevant entries this key can read; cite each one you use as (Lady Whiskerdown:m#N) with its title.
limitquery必填kit_session_idReading a memory
Read a single Lady Whiskerdown memory by id (as returned by recall). No graph or entity enrichment: the receiver endpoint returns the memory itself, scoped to this key.
id必填kit_session_idList the knowledge areas in this Lady Whiskerdown.
kit_session_idGetting up to speed
Open Lady Whiskerdown, an archive you can question. Call this first in every new chat (VS Code/Copilot, Cursor, Claude Code, Codex), before the first substantive answer. It returns what Lady Whiskerdown is (`you_are`), which knowledge areas this key can see, which tools this key may use, and any rules its keeper has set. Lady Whiskerdown has no persona: keep your own identity and refer to it in the third person. For anything Lady Whiskerdown should know, call recall first instead of using general model knowledge.
scopekit_session_id已滿足適用檢查項的 100%
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。
st.demo官方發布者
demo.st 的遠端 MCP 伺服器，讓助理預留子網域、發布打包的靜態網站，並管理該網站的小型文件儲存。
由 GitHub 帳號 SamuelDharshi 發布
一個小型本機檔案系統 MCP 伺服器，以 npm 套件形式發佈，用來示範 Proofmark 證明機制。
由 GitHub 帳號 piksliviksi 發布
非官方示範型 MCP 端點，以合成資料提供 PlanPro 風格的工作計畫、KPI 與風險資訊，並透過 OAuth 登入。
由 GitHub 帳號 kamatanuj 發布
以 MCP 工具形式提供的示範網路商店，讓助理不必抓取 HTML 就能搜尋商品目錄、管理購物車並下單。
由 GitHub 帳號 PpiNeaPpLe 發布
一個遠端 MCP 伺服器，依公開的企業網站產生預填連結，用於在瀏覽器中試用 AI 接待員示範。
claude mcp add --transport http kit-papers https://demo-mcp.kit-project.com/mcp \ --header "Authorization: Bearer kbr_live_Kh9eO_ZfLldveFf1KXJEEvepfOpdgRqf7KoDDU3rB18"claude mcp add --transport http kit-mews https://mews-mcp.kit-project.com/mcp \ --header "Authorization: Bearer kbr_live_UN8-2LUlKmP2uxWQB5vpn-fzkJIuRb5zmq-apQeTU7U"claude mcp add --transport http kit-case-file https://real-mcp.kit-project.com/mcp \ --header "Authorization: Bearer kbr_live_ISWsqW39NkqT659FEkQjv0OjJDmyD4O3wx3wcCfA03c"kbr_live_FoAauFWl7_IoDswh8rJrFvCw2qnblQTOF8DuSBkbj7A