[opensourcedex]

MineContext is a free, open source machine learning infrastructure project written in Python and released under Apache-2.0. It has 5,517 GitHub stars, 410 forks and 121 open issues, and was last pushed 4 months ago. On this registry it ranks #28 of 57 tracked projects in Machine Learning Infrastructure, with 5 head-to-head comparisons available. It gained 3 stars over the last 3 tracked days.

What is MineContext?

MineContext is an open-source, proactive context-aware AI partner that watches screen activity and turns it into insights, daily and weekly summaries, to-do lists, and activity records, built for people who want a local-first memory layer for their working day.

What it is

MineContext is a desktop AI partner built around context engineering. It captures screenshots and comprehends on-screen content to assemble a picture of the user's digital world, then uses an underlying context engineering framework to deliver insights, daily and weekly summaries, to-do lists, and activity records. The README describes future support for additional multimodal sources including documents, images, videos, code, and external application data, so screenshot capture is the current surface rather than the full range of sources.

The project lives in the AI and machine learning infrastructure category, and it exists to replace manual note-taking and personal knowledge management with an automated, always-running capture layer. Instead of asking users to file their own context, MineContext collects it in the background and resurfaces the useful parts at the moment of creation. It is shipped as an Electron desktop application with a Python backend, using TypeScript, React, and JavaScript on the front end, and embedding models and RAG on the retrieval side.

Key capabilities

  • Effortless collection: gathers and processes large volumes of context, with storage management designed so extensive collection does not add mental burden.
  • Proactive delivery: extracts daily and weekly summaries, tips, and todos from captured context and pushes them to the homepage.
  • Intelligent resurfacing: surfaces relevant context during creation without flooding the user with everything captured.
  • Context engineering architecture: supports the full lifecycle of multimodal, multi-source data, from capture through retrieval.
  • Local-first privacy model: the README documents a local-first design and a local AI model option alongside the step that enters an API key.
  • Screenshot-based capture: records screen activity as the primary context source, with documents, images, videos, code, and external application data named as future sources.
  • Desktop packaging: distributed as a downloadable application for Mac and Windows, with documented application packaging and backend debugging steps.

Who uses it and how

  • Individual knowledge workers who want an automatic record of their working day without maintaining a manual journal.
  • Creators and researchers who need relevant prior context resurfaced while writing or building.
  • Developers who run the Python backend server locally for configuration and debugging.
  • Privacy-conscious users who prefer the local-first and local AI model paths the project documents.
  • Contributors working on the Electron, React, and TypeScript front end or the Python backend, coordinated through the project's Discord, WeChat, Lark, and Red Note communities.

Getting started

Download the packaged desktop application for Mac or Windows, install it, enter an API key, and start recording. The README also documents running the backend server directly and working from source through the frontend build, dependency install, and application packaging steps.

How it compares

The README carries a comparison section titled "Comparison with Familiar Application", covering MineContext versus ChatGPT Pulse and MineContext versus Dayflow. Those two are the only comparable tools named in the source material, and the section frames MineContext as the open-source counterpart to them. Among the facts given, the supported contrast is that MineContext is Apache-2.0 and can run from source with its own backend and a local AI model option, so a user keeps the captured context rather than handing it to a hosted assistant.

When to use it — and when not to

A self-hoster has to run and configure the Python backend and supply an API key, so anyone expecting a zero-setup browser service will find the local path heavier than they want. Anyone unwilling to run an agent that records their screen should not adopt it, whatever the local-first design promises. The README also states that documents, images, videos, code, and external application data are future sources, so users whose context lives outside the screen should wait.

project readme (upstream, from github) — read inline

MineContext: Create with Context, Clarity from Chaos

An open-source, proactive context-aware AI partner, dedicated to bringing clarity and efficiency to your work, study and creation.

中文 / English

Community Best Practice · Report Issues · Feedback

[![][release-shield]][release-link] [![][github-stars-shield]][github-stars-link] [![][github-issues-shield]][github-issues-shield-link] [![][github-contributors-shield]][github-contributors-link] [![][license-shield]][license-shield-link]
[![][last-commit-shield]][last-commit-shield-link] [![][wechat-shield]][wechat-shield-link]

volcengine%2FMineContext | Trendshift

👋 Join our WeChat / Lark / Red Note Group

🌍 Join our Discord Group

🖥️ Download for Mac · 💻 Download for Windows

Table of Contents


🔗 Related Project: Check out OpenViking - An open-source Context Database designed for AI Agents. OpenViking unifies Memories, Resources, and Skills through a "file system paradigm", providing the infrastructure layer for sophisticated context management.


👋🏻 What is MineContext

MineContext is a proactive context-aware AI partner. By utilizing screenshots and content comprehension (with future support for multi-source multimodal information including documents, images, videos, code, and external application data), it can see and understand the user's digital world context. Based on an underlying contextual engineering framework, it actively delivers high-quality information such as insights, daily/weekly summaries, to-do lists, and activity records.

feature.gif

🚀 Key Features

MineContext focuses on four key features: effortless collection, intelligent resurfacing, proactive delivery, and a context engineering architecture.

  1. 📥 Effortless Collection Capable of gathering and processing massive amounts of context. Designed storage management enables extensive collection without adding mental burden.
  2. 🚀 Proactive Delivery Delivers key information and insights proactively in daily use. It extracts summarized content from your context—such as daily/weekly summaries, tips, and todos—and pushes them directly to your homepage.
  3. 💡 Intelligent Resurfacing Surfaces relevant and useful context intelligently during creation. Ensures assisted creativity without overwhelming you with information.
  4. 🎯 Context Engineering Architecture Supports the complete lifecycle of multimodal, multi-source data—from capture, processing, and storage to management, retrieval, and consumption—enabling the generation of six types of intelligent context.

🔏 Privacy Protection

Local-First

MineContext places a high priority on user privacy. By default, all data is stored locally in the following path to ensure your privacy and security.

~/Library/Application Support/MineContext/Data

Local AI model

In addition, we support custom model services based on the OpenAI API protocol. You can use fully local models in MineContext, ensuring that any data does not leave your local environment.

🏁 Quick Start

1. Installation

Click Github Latest Release to Download

Download APP

Note: Starting from v0.1.5, MineContext supports Apple notarization, so you no longer need to disable the quarantine attribute. If you're using an older version, please refer to the previous documentation for instructions.

2. Enter Your API Key

After the application launches, please follow the prompts to enter your API key. (Note: On the first run, the application needs to install the backend environment, which may take about two minutes).

We currently support services from Doubao, OpenAI, and custom models. This includes any local models or third-party model services that are compatible with the OpenAI API format.

We recommend using LMStudio to run local models. It provides a simple interface and powerful features to help you quickly deploy and manage them.

Considering both cost and performance, we recommend using the Doubao model. The Doubao API Key can be generated in the API Management Interface.

After obtaining the Doubao API Key, you need to activate two models in the Model Activation Management Interface: the Visual Language Model and the Embedding Model.

  • Visual Language Model: Doubao-Seed-1.6-flash doubao-vlm-model

  • Embedding Model: Doubao-embedding-vision doubao-emb-model

The following is the filling process after obtaining the API Key:

Enter API Key

3. Start Recording

Enter [Screen Monitor] to enable the system permissions for screen sharing. After completing the setup, you need to restart the application for the changes to take effect. Enable-Permissions

After restarting the application, please first set your screen sharing area in [Settings], then click [Start Recording] to begin taking screenshots. Screen-Settings

4. Forget it

After starting the recording, your context will gradually be collected. It will take some time to generate value. So, forget about it and focus on other tasks with peace of mind. MineContext will generate to-dos, prompts, summaries, and activities for you in the background. Of course, you can also engage in proactive Q&A through [Chat with AI].

5. Backend Debugging

MineContext supports backend debugging, which can be accessed at http://localhost:1733.

1.View Token Consumption and Usage 后台调试1

2.Configure Interval for Automated Tasks 后台调试2

3.Adjust System Prompt for Automated Tasks 后台调试3

🎃 Contribution Guide

🎨 Frontend Architecture

The MineContext frontend is a cross-platform desktop application built with Electron, React, and TypeScript, providing a modular, maintainable, and high-performance foundation for desktop development.

Core Tech Stack

| Technology | Description

readme truncated — read the full docs on github

Frequently asked questions

Is MineContext free to use?

MineContext is open source under the Apache-2.0 licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does MineContext do?

MineContext is your proactive context-aware AI partner（Context-Engineering+ChatGPT Pulse）

What is MineContext written in?

MineContext is primarily written in Python. Its source is publicly available at https://github.com/volcengine/MineContext, and it has 5,517 GitHub stars.