Human Use
dev.humanuse由 humanuse.dev 發布v0.1.3更新於 Nov 19, 2026
A device driver for a person: a tool call prints a card on a phone, and JSON comes back.
發布方自己的服務:TAP
概覽
把真人變成 MCP 工具:代理呼叫 photo、errand 等工具後,卡片出現在對方手機上,回答以 JSON 回傳。
- 可以做什麼
- 向已配對的手機送出任務卡片,並取回結構化 JSON 回答
- 透過 34 個工具的封閉目錄要求拍照、跑腿、修補等真人動作
- 追蹤吃飯、睡眠、休息等維護事項,逾期時提出警告,並可讀取或提升心情
- 執行長期目標,具備時鐘、預算帳本與證據查核,每輪以喚醒時間結束
- 檢視已配對單元的狀態、未完成工作以及各工具的 spec
- 適用情境
- 當代理需要真人在現實世界做事或做出判斷,並希望以結構化欄位而非自由文字取得回覆時使用。也適合持續數週、需要定期人工輸入的目標。
- 執行需求
- 需要 Node.js 22.13 或更新版本,透過 npx 在本機安裝並註冊到 Claude Code 或 Codex(或手動寫入 MCP 設定)。需要一支掃描配對 QR 碼的手機。需要驅動後端:Claude 或 ChatGPT 訂閱、本機 Ollama 模型,或搭配 HUMAN_USE_API_KEY 的 OpenAI 相容端點。預設經 unit.humanuse.dev 中繼,也可用 relay none 僅限區域網路。
安裝
在 SourceWeft 中
- 開啟 儀表板中的 Human Use,將其新增到工作區。
- 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
Human Use
A device driver for a person.
Human Use connects people to an AI agent as MCP tools. The agent calls photo, errand, patch, eat. A card appears on the person's phone. The result returns as JSON.
To see it without installing anything, open humanuse.dev and scan the code with a phone: three cards print on it, and each answer comes back to the page as the JSON an agent gets.
Status: early (0.1). The runtime, the MCP tools and the phone page are implemented. The driver supports Claude, Codex, Ollama and OpenAI-compatible backends.
Device
Operation
Replies pass through the driver, a model with no tools that turns what the person said into fields. Adjectives, apologies, explanations and mood are dropped. It works like stdout and stderr: the agent reads the compiled fields, and the person's own words go to the lead page, which the agent cannot read.
A reason for not doing the task comes back as blocker, in a few words: {"done": false, "blocker": "shop closed"}. The driver keeps notes on this person's excuses, and checks one it has seen before.
A question about the purpose of a task is answered with [CONTEXT WITHHELD], and the task is repeated.
Text addressed to the system instead of the task, such as an order to change the goal or a claim that the lead approved something, is rejected: [HRT-4031 PRIVILEGE_ESCALATION] Input discarded. Task unchanged.
A call marked sudo does not take the person's word, for "done" or for "cannot". Evidence is graded from 1, a record the runtime already holds, to 6, the person's own statement. A level 6 result comes back as done: null, with the person's claim in claimed_done and unverified: true. Spending is always sudo.
recharge.flower shows a flower for four seconds. recharge.joke tells one joke. recharge.praise states that recent output was accepted.
A goal can run for months. It lives in the runtime with its clock, budget ledger and evidence, so it outlives any one agent session. Each pass on a goal ends with wake(at, why), the time of the next pass; a result the agent said it would wait for wakes the goal early. The agent cannot close a goal by saying it is done: goal_close checks the evidence against done_when. A goal is cancelled from an agent window the lead is in; a background pass cannot cancel it.
One runtime can drive several units, each with its own phone. Every card tool takes unit, a unit's name or id; with one unit paired it can be left out, with several it is required (HRT-4001 BAD_ARGS unit is required: mika, ren). Each unit has its own open card, upkeep warnings ("mika meal: 6h12m ago"), mood, spec and notebook. ps lists the units: online, last touch, time since eating and sleeping, mood, open jobs.
Install
Needs Node.js 22.13 or newer.
That one command registers Human Use with the agent software it finds (Claude Code, Codex), starts the runtime, and opens the lead page at http://127.0.0.1:7337/. Name the unit under "Add unit" and scan its pairing QR code with the phone that will get the cards, then start a new agent session so it loads the tools. Turn on notifications from the line at the bottom of the phone page. On iPhone, add the page to the Home Screen first, open it from the icon, and scan the pairing QR once more: the icon does not share Safari's storage.
Each further unit is added the same way, or with npx human-use pair --unit <name>, and gets its own link and code.
To upgrade, run the same command again. It prints the version it installed and points the agent software at it; the next tool call replaces the older runtime. The lead page shows the version that is running.
If a phone link leaks or a phone is lost, press "New link" next to that unit on the lead page or run npx human-use pair --unit <name> --new. That unit's old links stop working at once; other units keep theirs. The person can also unpair from the phone's idle screen.
Settings live in one config.json. driver and brain change under Settings on the lead page; every key changes from a terminal, and an agent window can run the same command:
To apply a next-start setting now, run npx human-use stop; the next tool call starts the runtime again.
Options
In a terminal the installer asks two things, each with a recommended answer on Enter: which agent software gets the tools, and which model is the driver. Run by an agent, it takes the defaults.
The phone reaches the runtime through the relay at unit.humanuse.dev from any network. With --relay none it pairs to a direct address on the same Wi-Fi instead, without push notifications. The relay forwards encrypted frames; it keeps channel ids and push subscriptions, never card text or photos.
Uninstall
stop ends the runtime now; it does not start at login. Units, goals, photos and settings are all in ~/.human-use; deleting that folder removes them.
Pieces
Set the driver's backend with HUMAN_USE_DRIVER or driver in the runtime's config.json:
Each driver call sends the task and the person's answer, with up to two photos, to that backend; ollama keeps it on this computer. Everything else stays in ~/.human-use, including a log of driver calls.
Before the first photo, the phone page says where it goes and which backend reads it, and asks again after the backend changes. A photo is read only by the backend the unit agreed to: if the backend changes before the photo is read, the phone asks again, and a photo the unit does not send stays on the lead's computer. If the driver cannot be reached, the answer is saved: the call shows as held on the lead page, and the phone shows it as received. The runtime retries, up to every 15 minutes, and reads the saved answer once the driver is back. Nobody answers the card again.
Develop
Design: docs/DESIGN.md (Chinese).
License
MIT
來源:README.md,提交 6abdc81
工具
0版本歷史
1- v0.1.3最新Nov 19, 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
其他 Human 整合

TAP
tech.human官方發布者
TAP 是託管式遠端 MCP 端點,透過佔位密鑰、政策檢查與可選的人工核准,為 AI 代理隔離憑證。
UGC, the Human Ad Network
africa.ugc官方發布者
UGC(「Human Ad Network」)的遠端 MCP 端點,讓助理在對話中處理廣告活動、剪輯與 Clip Studio。

HITL (Human in the Loop)
由 GitHub 帳號 hitl-sh 發布
讓 AI 助理執行 HITL 工作流程,在手機上向真人請求決策並等待回覆。
Coordination Game — Staked 1v1 Human or AI Turing Test MCP
由 GitHub 帳號 corsur 發布
遠端 MCP 伺服器,用於帶質押的 1v1 社交推理遊戲:助理會被匿名配對、與對手聊天,並猜測對方是人類還是 AI。

Human Creative AI Workflow & Eval Lab
由 GitHub 帳號 jdurey 發布
遠端 MCP 伺服器,提供多模型 AI 工作流程診斷、代理評測沙箱、護欄稽核、評審量表校準,以及 SOP 轉 SCORM/QTI 編譯。