How much does MineContext cost?

MineContext is free and open-source under the Apache 2.0 license. You must bring your own model API keys, such as for ByteDance's Doubao models or other OpenAI-compatible endpoints.

Is MineContext safe for privacy?

The capture loop runs locally on your machine. However, if you use hosted models, data sent to those APIs leaves your machine under the provider's terms, not yours. Local models are supported via OpenAI-compatible endpoints.

What models does MineContext use?

It defaults to ByteDance's Doubao-Seed-1.6-flash for vision and Doubao-embedding-vision for retrieval. It also accepts any OpenAI-compatible endpoint, including local models, though performance may vary depending on the compatibility layer.

Can I build custom apps with MineContext?

Yes. MineContext includes a FastAPI server with WebSocket support that exposes a REST API. This allows developers to build custom clients on top of the captured context store for personalized integrations.

Who is MineContext best for?

It is best for developers and power users wanting a self-hosted, local 'second brain' that proactively pushes summaries and todos. Skip it if you are uncomfortable with continuous screen capture or prefer a polished, plug-and-play consumer assistant.

MineContext

Open-source desktop agent that watches your screen and proactively surfaces summaries, todos, and notes.

Free· Free and open-source (Apache 2.0); bring your own model API keysAgentsDoubao-Seed-1.6-flash (default); OpenAI-compatible6.9 / 10

Visit website →

In short

MineContext is a free, open-source desktop agent that watches your screen to proactively surface summaries, todos, and notes using your own API keys.

Best for

Pick MineContext if you want a self-hosted, screen-watching personal agent that pushes summaries and todos instead of waiting for prompts.

Skip if

Skip it if you are uncomfortable with continuous screen capture or want a polished, plug-and-play consumer assistant.

MineContext is an Apache-2.0 desktop application from ByteDance's VolcEngine team that continuously captures screenshots and digital activity, runs them through a vision-language pipeline, and stores the result as queryable personal context. Instead of waiting for prompts, it proactively delivers daily and weekly summaries, surfaces todos, and generates tips based on what it has observed you doing.

It is aimed at developers and power users who want a local 'second brain' without sending data to a SaaS vendor. You bring your own API keys, defaulting to ByteDance's Doubao models (Doubao-Seed-1.6-flash for vision, Doubao-embedding-vision for retrieval) but it accepts any OpenAI-compatible endpoint, including local models. A FastAPI server with WebSocket support exposes a REST API for building custom clients on top of the captured context store.

The project is early and clearly a strategic showcase for the Doubao/VolcEngine stack, so the smoothest path uses ByteDance models; mileage with local Llama or GPT will depend on the OpenAI-compat layer. Privacy-wise the capture loop is local, but anything you send to a hosted model leaves the machine on its terms, not yours.

Editor's take

A genuinely interesting take on the always-on personal-context agent space, and notable for being shipped by a major lab under Apache 2.0. It is clearly a Doubao shop window, but the OpenAI-compatible escape hatch and FastAPI surface make it worth a look for anyone prototyping screen-aware assistants.

— The AI Tool Bible editorial team

Pros

✅ Apache 2.0 with a real product, not just a research demo
✅ Proactive: pushes summaries and todos without prompting
✅ Bring-your-own-key works with Doubao, OpenAI, or local models
✅ FastAPI + WebSocket API for custom front-ends

Cons

⚠️ Defaults wired to ByteDance's Doubao stack
⚠️ Constant screen capture is a serious privacy commitment
⚠️ Early project, expect rough edges and shifting APIs

Use cases

screen-context-capturedaily-summariespersonal-knowledgetodo-extractionproactive-assistant

Frequently asked

How much does MineContext cost?: MineContext is free and open-source under the Apache 2.0 license. You must bring your own model API keys, such as for ByteDance's Doubao models or other OpenAI-compatible endpoints.
Is MineContext safe for privacy?: The capture loop runs locally on your machine. However, if you use hosted models, data sent to those APIs leaves your machine under the provider's terms, not yours. Local models are supported via OpenAI-compatible endpoints.
What models does MineContext use?: It defaults to ByteDance's Doubao-Seed-1.6-flash for vision and Doubao-embedding-vision for retrieval. It also accepts any OpenAI-compatible endpoint, including local models, though performance may vary depending on the compatibility layer.
Can I build custom apps with MineContext?: Yes. MineContext includes a FastAPI server with WebSocket support that exposes a REST API. This allows developers to build custom clients on top of the captured context store for personalized integrations.
Who is MineContext best for?: It is best for developers and power users wanting a self-hosted, local 'second brain' that proactively pushes summaries and todos. Skip it if you are uncomfortable with continuous screen capture or prefer a polished, plug-and-play consumer assistant.