# Screenpipe：开源本地优先AI记忆工具，记录工作流生成智能体

- 来源：Rohan Paul (@rohanpaul_ai)
- 发布时间：2026-07-15 04:28
- AIHOT 分数：38
- AIHOT 链接：https://aihot.virxact.com/items/cmrl5782d00a3bilm71lmp83c
- 原文链接：https://x.com/rohanpaul_ai/status/2077128225030107481

## AI 摘要

Screenpipe 发布开源、本地优先的 AI 记忆层工具，GitHub 获 20K+ 星标、1,900+ 分支和 130+ 贡献者。它记录用户日常工作，生成可搜索的记忆、会议跟进、每日总结、个人 CRM、SOP 及 AI 智能体。用户可控制录制内容，排除特定应用、窗口和 URL，并自主选择数据存储位置。企业可跨机器映射重复工作流，保留流程知识并暴露瓶颈。

## 正文

So much great work is happening on the memory layer of AI.

And a local-first memory for AI just launched， a company brain built from how work actually happens.

@screentime ： open source， local-first， 20K+ GitHub stars， 1，900+ forks， and 130+ contributors

This AI agent has a local memory of people's daily work. That memory can produce meeting follow-ups， daily recaps， personal CRM entries， SOPs， and agents.

Users control what gets recorded， can exclude apps， windows， and URLs， and choose where their data lives.

Companies can map repeated workflows across machines， preserve process knowledge， and expose bottlenecks.

Try screenpipe and name the agent you would build with a complete work memory.

### 引用推文

> screenpipe (YC S26)：introducing screenpipe: it records and learns how you work and turns it into a searchable memory, SOPs, and AI agents open source, local-first, 20K+ GitHub star...