Overview
put·here is a local-first spatial knowledge workbench for Mac users, built to organize material scattered across web pages, notes, screenshots, images, and folders. It places content on a freely arrangeable canvas; cards, groups, and links help you structure ideas, with optional AI search, summarization, and research. Core features — Spatial material canvas: drag text, links, images, PDFs, and files onto the canvas and place them freely so relationships are obvious. Cards and real file management: text is saved as Markdown; images and files keep their original formats; each canvas maps to a local Finder folder for backup and migration. AI organize and semantic search: AI can read the canvas, auto-group, summarize, and brief, and search across canvases by meaning. Sourced AI research: hand a question card to AI; it reads existing material, searches the web, organizes findings in a separate workspace, and keeps citations. Multiple model hooks: built-in AI, or connect DeepSeek, OpenAI, Claude, Kimi, Zhipu GLM, Tongyi Qianwen, OpenRouter, or local Ollama. Local-first privacy: no account required, no cloud sync; use built-in AI, your own API key, or fully local models.
Connected profiles
More Productivity products
Sources · 0Sources & provenance
English text is maintained separately from the original record. Consult the original source before citing a fact.
No source links are available for this profile.
Original source text
Names may use phonetic renderings when no English name is supplied. The original wording is retained below.
put·here 是一款面向 Mac 用户的本地优先空间式知识工作台，适合整理散落在网页、笔记、截图、图片和文件夹中的资料。它把内容放进可自由摆放的画布，通过卡片、分组和连线帮助用户梳理思路，并提供可选的 AI 搜索、总结和资料研究能力。核心功能空间式资料画布：将文字、网页链接、图片、PDF 和文件拖入画布，自由摆放位置，让资料之间的关系一目了然。卡片与真实文件管理：文字以 Markdown 保存，图片和文件保留原格式；每个画布对应本地 Finder 文件夹，便于备份和迁移。AI 整理与语义搜索：AI 可以识别画布内容，自动生成分组、摘要和简报，也能跨画布按语义查找相关资料。带来源的 AI 研究：选中一个问题卡片交给 AI，系统会读取已有资料并搜索网页，在独立工作区整理研究结果，同时保留引用来源。多种模型接入：支持内置 AI，也可以接入 DeepSeek、OpenAI、Claude、Kimi、智谱 GLM、通义千问、OpenRouter 或本地 Ollama 模型。本地优先与隐私控制：无需注册账号，不使用云端同步；用户可以选择内置 AI、自备 API Key，或完全使用本地模型。