#215 · Primary category： Knowledge Base & RAG
Memory-Cache
MemoryCache is an experimental development project to turn a local desktop environment into an on-device AI agent
Project last updated：04/19/24
GitHub Stars
564
Forks
25
Contributors
5
License
MPL-2.0
Why we included this project
Memory Cache is a Firefox extension that saves the page you are reading as a PDF into a folder a local privateGPT instance watches, so the content lands in your on-device knowledge base. If you run a local language model, this is a lightweight way to feed it the articles and docs you actually browse without moving files by hand. The setup is clearly experimental. It needs a patched Firefox build to save silently and targets an early privateGPT version, so it suits tinkerers comfortable with symlinks, shell scripts, and a bit of friction. The real payoff is the idea: everyday browsing becomes a steady stream of source material for a private, local retrieval setup.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
ragflow
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
Understand-Anything
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
crawl4ai
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
docling
Get your documents ready for gen AI
anything-llm
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience