# volcengine/MineContext

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

Repository: https://github.com/volcengine/MineContext
Canonical: https://ross.abutalabs.com/products/minecontext
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agent, context-engineering, electron, embedding-models, memory, proactive-ai, python, python3, rag, react, vector-database, vision-language-model, javascript, typescript
Last push: 2026-05-07T13:23:05+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 81, release rhythm 68, longevity 31
- inputs: {"age_days": 435, "days_push": 118, "days_rel": 217, "gap_med": 9.5, "n_releases_24m": 9}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5490, forks 409 (observed 2026-08-28T04:09:19.778048+00:00)

## What it is
MineContext is an open-source, proactive context-aware AI partner that captures and understands your screen activity to surface relevant insights, summaries, and suggestions. It combines context engineering with RAG, local embedding models, and vision-language models in a local-first desktop application built with Python and Electron.

## Use cases
- automatically summarize what I did on my computer today
- get proactive AI suggestions based on my screen activity
- search my past screen history with natural language
- build a personal AI memory of my work and study
- run a local-first context-aware AI assistant on my desktop
- capture and index screen content for later retrieval

## When to choose
- you want a self-hosted, privacy-focused context capture assistant
- you need automatic activity summaries and proactive insights on macOS or Windows
- you want an open-source alternative to tools like Rewind or ChatGPT Pulse

## When to avoid
- you need a mobile or Linux-only solution
- you want a purely cloud-based assistant with no local setup
- you need a lightweight tool without screen capture or embedding models

## Facets
- artifact type: application
- maturity: active
- function: rag, vector-database, agent-framework, machine-learning, nlp
- domain: artificial-intelligence, developer-tools, self-hosted
- platform: windows, python, cross-platform
- tags: context-engineering, proactive-ai, screen-capture, memory, local-first, vision-language-model, embedding-models, ai-assistant, ai-agents, retrieval-augmented-generation, macos, electron, desktop

## Member repositories
- volcengine/MineContext (main) score 66

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:19.778048+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:56:21.514326+00:00, confidence not recorded.
  - readme: https://github.com/volcengine/MineContext (fetched 2026-08-28T04:09:19.778048+00:00, sha 877662e8344e)
- Data as of 2026-08-30T08:39:29.467469+00:00.