Kynoptic quietly records which apps you use, how active you are, and what your hardware is doing — into one local file that Claude, Cursor, or any MCP AI can query. No screenshots. No cloud. Nothing leaves your device.Kynoptic 在后台安静地记录：你用了哪些软件、多活跃、硬件状态如何——全部存进一个本地文件，Claude、Cursor 或任何支持 MCP 的 AI 都能直接查询。不截屏、不上云、数据不离机。
# What was I doing on the computer yesterday between 2 and 4 pm?我昨天下午两点到四点在电脑上干了什么？ According to Kynoptic:根据 Kynoptic 的记录： 14:02–15:10 VS Code — repo "kynoptic", 3 files, deep-focus session14:02–15:10 VS Code —— kynoptic 仓库，3 个文件，深度专注 15:10–15:26 Chrome · 23 tabs — MDN, GitHub issues15:10–15:26 Chrome · 23 个标签页 —— MDN、GitHub issues 15:26–15:58 Steam + game session — GPU 82%, 71°C, fan up15:26–15:58 Steam + 游戏 —— GPU 82%、71°C、风扇提速 source: local SQLite · 214 KB · never uploaded来源：本地 SQLite · 214 KB · 从未上传
Your AI assistant already knows everything on the internet. Kynoptic gives it the one thing it's missing: what actually happened on your machine.AI 助手知道整个互联网，却不知道你的电脑上发生过什么。Kynoptic 补上的正是这块空白。
You remember using it Tuesday afternoon — not the name. Your AI can now look it up instead of guessing.
记得周二下午用过，就是想不起名字。现在 AI 可以直接查记录回答你，而不是瞎猜。
Game stuttered at 9 pm? Check what the GPU, thermal, and active apps were doing at that exact minute.
晚上 9 点游戏掉帧？查一下那一分钟 GPU 温度、负载和前台应用，原因一目了然。
Daily and weekly activity summaries generated from your own data — no manual timers, no cloud tracking service.
基于你自己的本地数据生成每天/每周的活动总结——不用手动打卡，也不经过任何云服务。
Install the app, add one block to your MCP client config — your AI can now query your machine's history.装上应用，在 MCP 客户端配置里加一段——AI 就能查询这台机器的历史了。
{
"mcpServers": {
"kynoptic": {
"command": "kynoptic",
"args": ["mcp"]
}
}
}
# current machine status当前机器状态 $ kynoptic now # query history, join any signals查历史，任意信号组合 $ kynoptic query --from yesterday \ --metric gpu --join window # your data, plain SQL数据是你自己的，直接 SQL $ sqlite3 kynoptic.db "SELECT * FROM events"
Kynoptic knows what kind of thing happened — never what your screen showed. By design, there is nothing sensitive to leak.Kynoptic 只记录"发生了哪类活动"，永远不记录屏幕上显示了什么。从设计上就不存在可泄露的敏感画面。
Only aggregate counts of input events are stored. Password fields are excluded at the hook level — not even a count.
只存输入事件的聚合计数；密码框在系统钩子层就被排除——连计数都没有。
No pixels, no frames, no OCR. Nothing to replay, nothing to leak.
不抓像素、不录帧、不做 OCR。没有可回放的东西，也就没有可泄露的东西。
One SQLite file on your disk. No servers, no telemetry, no upload code path — verifiable in the open source.
一切都在你磁盘上的一个 SQLite 文件里。没有服务器、没有遥测、没有上传代码路径——源码公开可审计。
If you've seen screen-recording memory tools before: those rebuild what your screen showed. Kynoptic takes a different trade-off — structured events only, at a fraction of the cost and privacy surface. (Detailed numbers live in the repo's RESEARCH.md.)如果你见过录屏类记忆工具：它们重建的是"你的屏幕看过什么"。Kynoptic 走了另一条路——只存结构化事件，成本和隐私面都小一个数量级。（详细数据见仓库 RESEARCH.md）
| Screen recording + OCR录屏 + OCR | Video + LLM summaries录屏 + 大模型摘要 | Kynoptic — structured eventsKynoptic —— 结构化事件 | |
|---|---|---|---|
| What is stored存了什么 | Continuous screen video + OCR index连续屏幕录像 + OCR 索引 | Video chunks + screenshots, summarized by a VLM视频片段 + 截图，交给视觉模型总结 | Event-level records only — no pixels, ever只有事件级记录——完全不碰像素 |
| Running cost运行开销 | High — continuous OCR & indexing高——持续 OCR 与索引 | High — constant VLM API calls高——持续调用视觉模型 API | Near zero — lightweight native capture接近零——轻量原生采集 |
| Disk usage磁盘占用 | GB-scale per week每周 GB 级 | MB–GB scale with auto-cleanupMB–GB 级，依赖自动清理 | KB-scale per day每天 KB 级 |
| AI accessAI 接入 | API + MCPAPI + MCP | Markdown export only仅 Markdown 导出 | MCP server + CLI + open SQL schemaMCP 服务器 + CLI + 开放 SQL schema |
Nowhere. It stays in one SQLite file on your machine. There are no servers, no telemetry, and no upload code path — you can verify the process makes no outbound connections.哪也不去。就在你机器上的一个 SQLite 文件里。没有服务器、没有遥测、没有上传代码路径——你可以自己验证进程没有任何对外连接。
No screens, ever. Password fields are filtered at the hook level — typing in one produces no data at all, not even a count. A strict mode can additionally drop window titles.永不录屏。密码框在钩子层就被过滤——在密码框里打字不产生任何数据，连计数都没有。还提供严格模式，连窗口标题都不存。
Designed for near-zero overhead: no video encoding, no OCR, no cloud calls. Writes are batched to minimize disk I/O; typical storage is KB-scale per day.按"接近零开销"设计：没有视频编码、没有 OCR、没有云调用。写入批量落盘以减少 I/O；典型存储为每天 KB 级。
Those rebuild your screen — a replayable record of everything you saw. Kynoptic never captures pixels; it stores structured events: which app, how active, what the hardware was doing. A fitness tracker for your computer, not a black box for your screen.它们重建的是"你的屏幕看过什么"——一份可回放的记录。Kynoptic 从不抓取像素，只存结构化事件：哪个应用、多活跃、硬件在干什么。它是电脑的健身手环，不是屏幕的黑匣子。
Any MCP-capable client: Claude Desktop, Cursor, and other MCP hosts — via the built-in server. No MCP? Use the CLI, or run SQL against the open schema directly.任何支持 MCP 的客户端都行：Claude Desktop、Cursor 等，通过内置服务器接入。不用 MCP 也可以走 CLI，或直接对开放的 schema 跑 SQL。
Windows first — it's where the demand is, and plain Win32 APIs make the monitors truly lightweight. macOS and Linux are on the roadmap. MIT licensed, fully auditable.先做 Windows——需求在这里，而且原生 Win32 API 能做到真正的轻量。macOS 和 Linux 在路线图上。MIT 协议，完全可审计。
Leave your email and we'll tell you the day the installer is out. No spam, no newsletter — one launch email, that's it.留个邮箱，安装包发布当天告诉你。不发垃圾邮件、不发订阅——就一封上线通知。
Got it — see you at launch.收到，上线时见。
Prefer to watch the code? Star the repo instead — releases are announced there too.更想盯代码？直接 Star 仓库，Release 也会同步发在那里。