
SigRank SignalAF — AI Operator Cascade & Leaderboard
io.github.SunrisesIllNeverSee由 GitHub 帳號 SunrisesIllNeverSee 發布v1.0.47更新於 Oct 24, 2026
SigRank SignalAF on-device scanner — four-token cascade, leaderboard, 25 local tools.
發布方自己的服務:Ephemeris Time-Series Forecasting
概覽
本機 SigRank 掃描器,讓助理讀取你的 AI token 用量、計算級聯指標、查看公開排行榜,並可選擇發布經簽章的快照。
- 可以做什麼
- 檢查本機 AI 用量:從支援的工作階段日誌擷取 token 計數,依時間視窗與平台比較,也可用你提供的計數計算指標並取得標準紀錄定義。讀取公開結果:排行榜、營運者資料與同儕探索。探索可能的變化:診斷 token 級聯、模擬變更並提供改善建議。註冊與提交:用連線碼綁定裝置並發布簽章快照,支援試執行。
- 適用情境
- 適合讓助理稽核自己的 AI token 用量(輸入、輸出、快取寫入與讀取)、理解 Yield/Leverage/Velocity/SNR/10xDEV 指標,或與公開 SigRank 排行榜比較。發布為選用功能,只有想要排名條目時才需要。
- 執行需求
- 透過 npx 以 stdio 在本機執行,需要 Node.js 20 或更新版本,無需全域安裝。發布需在 signalaf.com 登入並建立連線碼以註冊裝置。未宣告任何環境變數或請求標頭。
安裝
在 SourceWeft 中
- 開啟 儀表板中的 SigRank SignalAF — AI Operator Cascade & Leaderboard,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
SigRank CLI & MCP
Read your local AI usage, inspect the token cascade, and optionally publish a signed snapshot to the SigRank leaderboard on SignalAF.
Website · Quickstart · MCP setup · Tool and adapter reference · Privacy
What it does
- Reads usage metadata from supported local AI session logs.
- Shows input, output, cache-write, and cache-read counts across available time windows.
- Calculates Yield, Leverage, Velocity, SNR, and 10xDEV locally.
- Provides a terminal dashboard and MCP tools for AI clients.
- Submits signed telemetry only when you choose to publish.
This evaluates observable token-processing patterns, not model quality, work quality, productivity, or business outcomes. An adapter may estimate a pillar when its source does not expose it separately; those limitations are documented in the adapter reference.
Get started
Requires Node.js 20 or later. No global install is required.
Explore locally
The dashboard includes Dashboard, Trends, Compare, Board, Watch, and Connect tabs. Use 1–6 or the arrow keys to switch, R to refresh, and Q to quit.
Publish your own snapshot
- Sign in at signalaf.com and create a connect code in Settings.
- Enroll this device, then inspect the dry-run payload.
- Submit when you are ready to publish.
Enrollment binds a device signing key to your operator account. The private key stays on your device. The server verifies and re-scores submitted telemetry; a local preview is not a guaranteed public rank.
For repeated use, an optional global installation provides the same commands:
Connect an MCP client
Add this server to your client's MCP configuration:
The entry point automatically runs an MCP stdio server when launched without a terminal. MCP tool names are called by the client; they are not shell commands.
For the full list, arguments, and adapter paths, see the CLI and MCP reference. Publishing through submit_verified requires confirm: true; dry_run: true inspects the payload without publishing.
Command guide
Optional usage proxy
Some clients do not persist all provider-reported usage in their session files. sigrank proxy can capture usage from compatible Anthropic or OpenAI API traffic when a client supports a custom API base URL.
The proxy is off by default and binds only to loopback. It forwards provider-bound request/response content and credentials in memory, but does not persist their content. Its local usage log contains token counts and metadata. See the privacy contract before using it.
How measurement works
Four token pillars feed the calculation:
This package distributes the Upsilon measurement engine through the sigrank CLI/MCP compatibility command. SigRank is the public leaderboard and proof surface on SignalAF. TTEOP defines the protocol semantics; MO§ES™ is the governance framework.
The implementation delegates canonical calculations through token-cascade to tteop-spec. See the TTEOP implementation profile and protocol compatibility notes.
Privacy
Local inspection does not publish your usage. Signed submissions include the four pillars plus account/device identifiers, signature, platform/version information, counts, and report metadata. Enrollment also sends a device label.
Prompt text, response text, source code, repository contents, and local file paths are not part of the ranked submission payload. The optional proxy's transient handling of content is separate from what is persisted or submitted.
Read the full payload and privacy details, and use submit --dry-run to inspect what would be sent.
Development
Run node index.mjs in a terminal for the dashboard, or configure the checked-out entry point in an MCP client. Release versions are managed by the repository's explicit publishing workflow; a documentation commit does not publish an npm release.
Related projects
- sigrank-app — SignalAF website, profiles, public API, and leaderboard.
- token-cascade — measurement implementation consumed by this package.
- TTEOP — protocol specification and semantics.
Contributing and security
See the contributing guide. Open bugs in GitHub Issues; report vulnerabilities privately through the security policy.
License
MIT.
來源:README.md,提交 871c40d
工具
0版本歷史
5- v1.0.47最新Oct 16, 2026
- v1.0.46Oct 14, 2026
- v1.0.44Oct 5, 2026
- v1.0.43Oct 5, 2026
- v1.0.12Sep 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
其他 Cascade 整合

Ephemeris Time-Series Forecasting
industries.cascade官方發布者
讓助理使用託管的時間序列基礎模型對數值序列進行帶預測區間的預測,並解讀、繪圖與追蹤結果。
SCRIPTMASTERLABS — Cascade Graph
com.scriptmasterlabs
遠端 MCP 伺服器,提供確定性的總體市場分析、SHA256 決策膠囊,以及可選的 Jev 評審團複核,建構於雜湊鏈校準日誌上。

cascade-img
由 GitHub 帳號 laffeyp 發布
讓助理撰寫 Midjourney 提示詞、透過 Discord 送出生成、用視覺檢查回傳的網格圖、裁切並清理最佳象限,並記錄有效的做法。

Forge Cascade MCP Memory Server
由 GitHub 帳號 SunFlash12 發布
回傳 Forge/Froggit 的公開購買路徑、定價與付費結帳連結,讓助理依買方情況推薦購買方案。