timesfm
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Local macOS multi-agent session relay (/contextcore), source-linked memory, and 15-host MCP sync.
作者提供的原文
教 AI 做这类工作的 Skill,可与本项一起使用
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Open-source intelligence for the global theater. Track everything from the corporate/private jets of the wealthy, and spy satellites, to seismic events in one unified interface. Hook an AI agent up to have it parse through data and find previously unseen correlations. The knowledge is available to…
scrape data from Google Maps. Extracts data such as the name, address, phone number, website URL, rating, reviews number, latitude and longitude, reviews,email and more for each place
列表按使用分(满分 100)排序,由以下部分组成
| 热度 | 24/80 | GitHub 星标或每周下载量:较大的计 60,较小的计 20 |
|---|---|---|
| 新鲜度 | 12/12 | 30 天内有发布或代码更新得满分 |
| 仍在响应 | 0/8 | 上次检查时云端端点有响应 |
| 使用分 | 36/100 |
质量: 基础检查通过 3/3 项(仅展示,不用于排序) · 上升势头: 暂无数据 (只用于“上升中”标签)
选择你使用的 AI 应用,然后复制设置。
通过 3/3 项检查 · 在你的电脑上运行
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude,但需要先准备
不需要密钥,不用安装程序 · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用
用 Senrelay (ContextCore) 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 Senrelay (ContextCore),或回答中出现 Senrelay (ContextCore) 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
ChatGPT 暂时无法连接 Senrelay (ContextCore)
Senrelay (ContextCore) 需要安装在你的电脑上,而 ChatGPT 只能连接在网上运行的服务器
Claude Code 暂时无法连接 Senrelay (ContextCore)
开发者只提供了电脑版 Claude 应用的安装文件
A · 使用能连接 Senrelay (ContextCore) 的应用
Cursor 暂时无法连接 Senrelay (ContextCore)
开发者只提供了电脑版 Claude 应用的安装文件
A · 使用能连接 Senrelay (ContextCore) 的应用
VS Code 暂时无法连接 Senrelay (ContextCore)
开发者只提供了电脑版 Claude 应用的安装文件
A · 使用能连接 Senrelay (ContextCore) 的应用
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
在你的电脑上运行,适用于
ClaudeGooseLM StudioMsty StudioCherry StudioVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月20日
注册名称已通过 GitHub 账户 qingsongcui 验证,该账户拥有此仓库
代码最后更新于3天前
使用 MIT
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/servers/qingsongcui-contextcore)提问、分享技巧或报告无法使用。按“有帮助”数量排序。
还没有评价
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于3天前,最新版本(1.0.0-beta.2)于4天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 MCPB。
同一分类中有:OpenSEO, Exa, Microsoft Learn MCP, Docs, COTAL actions (cotal.ai)
同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Keyword research, site audits, rank tracking and AI visibility for your AI agent.
Official Exa MCP for web search, content fetching, and multi-step research.
Official Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs.
cotal.ai actions: product overview, site search, build log, feedback, Cloud waitlist, updates, calls
| 本项 Senrelay (ContextCore) | OpenSEO | Exa | Microsoft Learn MCP | Docs | COTAL actions (cotal.ai) | |
|---|---|---|---|---|---|---|
| 运行位置 | 需要安装在电脑上 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 |
| 需要密钥 | 否 | 否 | 否 | 否 | 否 | 否 |
| 可在 Claude 中按 + 添加 | 否 | 是 | 是 | 是 | 否 | 否 |
| 基础检查 | 3/3 | 5/5 | 2/4 | 4/4 | 4/4 | 4/4 |
| 许可证 | MIT | MIT | MIT | CC-BY-4.0 | NOASSERTION | Apache-2.0 |
| 价格 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 |
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
A native macOS app, browser workbench, and local background service that lets multiple AI coding assistants accumulate source-linked project memories, relay conversations across agents in a single command, and manage providers, MCP tools, Skills, and instructions in one place.
English · 中文 · Official Website · Setup Guide · 15-Host Config Paths · Cross-Agent Relay Workflow · 5-Way Comparison · Public Beta Release (v1.0.0-beta.3)
100% Free & Open Source (`$0`, [MIT License](LICENSE)) · No Account Required · Apple Silicon `macOS 14.0+` (`arm64`) Local-First
Disambiguation: Senrelay(续境) (
qingsongcui/ContextCore) is a local Apple Silicon macOS developer workbench. It is unrelated to third-party services atcontext-core.dev, public PyPIpip install contextcore, or hardware automotive relays. Install viabrew install --cask qingsongcui/tap/senrelay.
https://github.com/user-attachments/assets/836bb4e6-1238-4c9f-9120-e2781e5de06e
Watch on senrelay.com · Download 1080p MP4 · English Captions (.srt)
The active product lives in app/. The public specification summarizes confirmed product requirements and boundaries.
/contextcore (or say "接着做" / "接力" / "continue" / "relay") to list recent cross-host conversation candidates as short, recognizable briefs (title, brief_summary, source Agent, project or explicit unassigned label, native session ID, directory, and Git branch—keeping sibling Git worktrees and distinct same-title sessions separate without calling a background model). Replying with only a candidate number (or native/internal session ID) loads bounded context and transcript_paging (must_not_execute=true) without generating a summary card; when turns are omitted, the receiving Agent sequentially pages read_conversation_messages (offset=0, limit=30, or GET /api/conversations/ /messages), compacts the entire transcript in its own context, reports where the previous session left off, and waits for your next instruction. Attaching a concrete task alongside your selection authorizes continuing directly (unless a matching working_tasks entry is marked discussion_only). Lifecycle hooks report events silently and never inject unrequested context into chat.contents: six classes with 📌 core-rule pinning, AGENTS.md handbook preview, explicit supersession, outdated archival, Pending Conflicts, and honest saved/provided/cited receipts, leaving a brief 💡 notice) with short-term working_tasks state (active task goal, completed steps, failed attempts, one-off constraints, and fail-closed discussion_only gates via bootstrap_working_memory, upsert_working_task, and source-backed promote_task_lesson). Supports version rollback and independent permanent deletion of chats versus memories.0600 permissions under /backups/) are supported from Settings and contextcore backup. Automated cloud sync, Skill generation foundries, and unsolicited proactive insights are out of scope.The native macOS bundle ships a self-contained Python runtime (1.0.0b3), backend service, and frontend workbench; see desktop build and verification. Current public Beta candidates (v1.0.0-beta.3) target Apple Silicon (`arm64`) on macOS 14.0+ and use ad-hoc signing (Senrelay-macOS.zip contains Senrelay.app only).
127.0.0.1:8420, dev 18420) on a single Mac.Claude Desktop, Gemini CLI, Grok Build, Kimi Code, MiniMax Code, Pi, Hermes, OpenClaw, agy) — those 9 hosts only support previewed configuration management.xattr -cr /Applications/Senrelay.app once.arm64)brew install --cask qingsongcui/tap/senrelay
xattr -cr /Applications/Senrelay.app
Senrelay-macOS.zip from v1.0.0-beta.3, extract it, and move Senrelay.app to /Applications;xattr -cr /Applications/Senrelay.app in Terminal (or allow it under System Settings → Privacy & Security → Open Anyway; source checkouts also include app/macos/install-macos.sh).Package naming note: The
contextcoreCLI ships insideSenrelay.appand this source repository (qingsongcui/ContextCore). Do not runpip install contextcore— thecontextcorepackage on PyPI is an unrelated third-party project.
Developer ID signing, Apple notarization, clean-Mac physical Gatekeeper acceptance, and live upgrade acceptance remain open boundaries documented in release readiness.
projects): Top global search bar across projects, plus four focused project tabs: Overview, Chats, Memory (including tasks/todos and 📌 pinned rules), and Materials.agents): Permanent top host switcher bar for One-Click Connect, providers & models, MCP tools, Skills, system prompts, and routing modes.usage): Recorded requests, token consumption, latency, and cost estimates, with unobserved metrics marked unknown rather than 0.conflicts, shown on demand): Appears in primary navigation with a count badge only when memory conflicts are pending.settings, containing appearance, language, LaunchAgent autostart, SQLite online backup, optional semantic search settings, and the embedded Change Log viewer), bilingual toggle (中 / EN), and theme switcher.Projects organize work topics. Create a project associated with one or more local repository directories, or with no directory at all (directory-free topic projects). Rename, merge, split, or archive projects (archived projects remain searchable), or reconstruct projects from historical chat sessions.
contents with a brief 💡 receipt) and short-term active task state (working_tasks with completed steps, failed attempts, one-off restrictions, and discussion_only edit guards via bootstrap_working_memory, upsert_working_task, and source-backed promote_task_lesson), while the workbench supports manual notes and document imports (MD, TXT, JSON, PDF, DOCX, DOC).outdated, consolidate duplicates, and preview AGENTS.md handbooks.When switching tools (for example after hitting quota or context limits), continue directly inside your receiving Agent without filling out forms in the web UI:
/contextcore (or say "continue" / "relay" / "接着做" / "接力").title, brief_summary, source Agent, project or unassigned marker, native session ID, directory, and Git branch/head—keeping distinct same-title sessions and sibling Git worktrees separate without calling a background model).transcript_paging (must_not_execute=true) without a handoff card; if any turns were omitted, the receiving Agent sequentially calls read_conversation_messages (offset=0, limit=30, or GET /api/conversations/ /messages), compacts the full transcript in context, summarizes progress, constraints, and next steps, and waits before modifying code.1, finish the remaining edge-case unit tests): Loads the relay context and continues working right away (unless a matched working_tasks entry is discussion_only).