一个自动化智能体,每天从Coast屏幕历史中重建昨天未完成的任务,生成带裁剪截图证据的回顾页面,并通过推送通知发送到手机。

Stars

8

7 天增长

暂无数据

Fork 数

0

开放 Issue

0

开源协议

暂无数据

最近更新

2026-07-29

AI 仓库情报摘要
FR-AI / ANALYSIS

为什么值得关注

这是一个实用的现实世界自动化项目,结合了屏幕记录、AI智能体编排和个人生产力,具备隐私优先的设计和反馈循环,能优化未来的审计。

适合谁使用

  • 构建AI智能体工作流和自动化的开发者
  • 追踪数字活动的生产力爱好者
  • 熟悉launchd和CLI工具的macOS用户
  • 使用Coast屏幕追踪并希望获得高级回顾功能的用户

典型使用场景

  • 每天早上回顾未完成的沟通和工作进度
  • 追踪需要后续跟进的邮件、消息或任务
  • 自动记录并归档每日未完成事项,附带视觉证据
  • 建立个人问责和闭环的习惯

项目优势

  • 使用视觉验证确保裁剪截图确实显示所声称的证据
  • 并行运行两个子智能体,分别处理沟通和工作进度中的未完成事项
  • 隐私敏感:所有敏感数据保留在本地机器上,并被gitignore忽略
  • 集成推送通知、网页界面和双向同步,实现无缝交互

使用前须知

  • 与Coast.app、OpenCode和macOS(launchd)紧密耦合,跨平台使用困难
  • 需要大量设置,包括多个CLI工具和私有托管服务器
  • 截图裁剪、OCR和视觉分析可能占用较多资源,在性能较弱的机器上会有负担

README 快速开始

coastcap — morning audit

Every morning, an agent reconstructs yesterday from my Coast screen history, finds the loose ends — things I left unfinished, never sent, or forgot to follow up on — and publishes a recap page with cropped screenshot evidence. A push notification lands on my phone when it's ready. Marking an item complete on the page feeds back into the next morning's audit.

(full quality: docs/demo.mp4)

How a morning runs

  1. 9:00 — launchd starts a headless OpenCode run (run.sh + prompt-template.md) with a random jitter.
  2. The agent reads its memory: previous audits (history/), the previous recap JSON, and which items I marked complete on the page (state/interactions.json).
  3. It dispatches two subagents in parallel over the Coast CLI: one hunts communication loose ends (unsent replies, people waiting on me), the other work-in-progress loose ends (abandoned terminals, half-typed prompts, errored flows). Carryover items from previous days get re-verified against the new day's evidence.
  4. For the items where a screenshot helps, it locates the exact frame, crops to the evidence region using Coast's OCR box coordinates (scripts/crop-evidence.py), then looks at each crop with vision and only ships images that actually show the claimed evidence.
  5. It writes site/data/.json. The Bun server renders it as a per-day page (/july-28th-2026) with an archive at /.
  6. A 10-minute two-way sync (scripts/sync.sh) pushes the site to an exe.dev box (auth-gated HTTPS) and merges item interactions in both directions. The first sync after a new recap fires a Hark push notification with a tap-through to the day's page.
  7. Tapping a row on the page blurs it and offers Mark complete — that interaction syncs back and becomes "cleared" in tomorrow's audit.

Components

PathWhat it is
run.shMorning entrypoint: date substitution, jitter, headless opencode2 run --auto
prompt-template.mdThe agent's brief: memory, subagents, synthesis rules, crop verification, output schema
scripts/crop-evidence.pyFrame + on-screen text → OCR-box union → padded sips crop
scripts/sync.shTwo-way state merge + site push to the box + once-per

相关仓库与替代方案

根据分类、Topic 和编程语言匹配的相似项目。

MoonshotAI
精选
MoonshotAI GitHub avatar

Kimi-K3

Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.

AI 与机器学习AI 智能体
3,348
jamesob
精选
jamesob GitHub avatar

local-llm

A comprehensive guide for building and configuring a high-end local machine to run state-of-the-art LLMs, with detailed hardware choices, BIOS tuning, and Docker-based model serving.

AI 与机器学习大语言模型
1,660
Blaizzy
精选
Blaizzy GitHub avatar

nativ

Nativ is a native macOS app that lets you run AI models locally on Apple silicon, offering chat, model management, performance analytics, and an OpenAI/Anthropic-compatible API server.

AI 与机器学习AI 视觉与语音
985