Skip to content
repository radar
RAG & Memory

🧠MineContext

ACTIVE STEADY

volcengine/MineContext

MineContext is your proactive context-aware AI partnerContext-Engineering+ChatGPT Pulse

⭐ Popular: 5k stars, gaining about 8 a week

View on GitHub ↗

repo profile

vintage 2025 1 year old
delivery product
language Python
license Apache-2.0

momentum

total stars 5k
stars added last week +8
binary downloads 10k total · GitHub releases
commits / week 0 steady
issues closed 43% ~3d to close, median
contributors 33
release cadence fortnightly
last activity 3mo ago

durability

backing company-owned ByteDance
openness permissive
bus factor 4 distributed
top-author share 25% 6 mo

bus factor = how many people it takes to cover more than half the commits (6 months). 1 is a solo project; higher means the work is spread across a team. top-author share is the single busiest author's slice of those commits.

since we covered it

monthly average + 212/mo (+6%/mo) · + 2k total since PR#21

why it's a big deal

  • Turns passive screen activity into structured output by capturing screenshots at set intervals and generating daily and weekly summaries, todo lists, and activity records.
  • Runs local-first, keeping screenshots and derived context in local storage and supporting fully local model deployment via LMStudio for users who do not want data sent to external APIs.
  • Aimed at knowledge workers who want an automatic record of what they worked on without manually logging tasks.

under the hood

  • Splits into an Electron, React, and TypeScript desktop frontend and a Python FastAPI backend with WebSocket support, layered into capture, processing, consumption, and manager stages.
  • Stores relational data in SQLite and vectors in ChromaDB, using vision-language models such as Doubao-Seed-1.6-flash or OpenAI-compatible endpoints for analysis and Doubao-embedding-vision or OpenAI for embeddings.
  • Configured through YAML files for model selection, capture intervals, and localized prompt templates, with command-line arguments overriding config settings; licensed Apache 2.0.

Radar summary, generated from the project's public sources

star history

PR#21 · 4k5k now Jun 2025Aug 2026
  1. PR#21 4k 2025-11-12
  2. now 5k + 2k since first covered

curve is sampled from GitHub's star history, plus our own daily readings since we covered it; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.

understory

Better known than its recent output, coasting a little on attention.

-39 understory score output 6 · clout 45
Aug 2025 Jul 2026
  • output, commits & releases
  • clout, star velocity

output = commits & releases; clout = star velocity, both 0 to 100 monthly indices; the gap where output runs above clout is the understory. The understory →

covered in

  • PR#21 2025-11-12 below the radar

    Your digital-workspace AI sidekick

similar projects

compare these →
  • 🧠 Memori

    3× the stars

    Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises.

    16k ACTIVE
  • 🗜️ headroom

    12× the stars

    Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

    66k ACTIVE
  • 🧠 Mem0

    12× the stars

    Universal memory layer for AI Agents

    63k ACTIVE

comments

Sign in with GitHub to add your blip on MineContext.

loading comments…