Awesome MCPKnowledge & Memory

ccbikai/github-stars

⭐ 114 JavaScript added to this list on 2025-05-14 repository created 2024-12-01

GitHub Stars MCP Server turns a personal collection of GitHub stars into a searchable knowledge base that an AI client can query in plain language. The project has two halves. A scheduled job uses the GitHub API to fetch every repository the account has starred, pulls the README from each one, processes the text together with repository metadata, and uploads the result to a Cloudflare R2 bucket. A Cloudflare AutoRAG instance then indexes that bucket and builds the embeddings used for semantic retrieval. The second half is a Cloudflare Worker that speaks the Model Context Protocol over Streamable HTTP and exposes a single tool, search_github_stars, which takes a natural-language query string and returns JSON with the matching repositories and the relevant README passages. Access to the worker is protected by an API key sent as a bearer token in the Authorization header, configured through the MCP_API_KEY variable. Refreshing is automated: a GitHub Actions workflow runs weekly to re-fetch the stars, upload the processed files to R2 and rebuild the AutoRAG index. Setup requires Node 22, the pnpm package manager, a GitHub personal access token with repo scope, and a Cloudflare account with an R2 bucket and an AutoRAG instance; the R2 account id, access key, secret and bucket name plus the GitHub token are stored as repository secrets, and the AutoRAG instance name is set through the AUTO_RAG_NAME environment variable on the worker. Local development uses pnpm dev:stars to fetch the stars and pnpm dev:mcp to run the server, and pnpm deploy publishes to Cloudflare Workers. It suits developers whose star list has grown past the point where the GitHub search UI is useful and who want an assistant to recall what they once bookmarked.

https://github.com/ccbikai/github-stars

mcp-servercloudflare-workersr2autoragsemantic-searchraggithubjavascript

Also in Knowledge & Memory

MemPalace/mempalace

MemPalace is an open-source, local-first AI memory system that stores and retrieves conversation history verbatim using semantic search, supporting pluggable backends like ChromaDB and integrating ...

siyuan-note/siyuan

SiYuan is a privacy-first, self-hosted personal knowledge management system featuring block-level referencing, Markdown WYSIWYG editing, and support for the Model Context Protocol (MCP).

topoteretes/cognee

Cognee is an open-source project that provides scalable and modular memory capabilities for AI agents using ECL pipelines, enabling efficient management and retrieval of past interactions and diverse data types.

vectorize-io/hindsight

Hindsight is an agent memory system designed to create smarter, learning AI agents by moving beyond simple conversation history recall to encompass a biomimetic storage architecture for long-term m...

screenpipe/screenpipe

Screenpipe is a local-first, AI-powered memory tool that records computer activity (screen, audio, accessibility tree) to provide a searchable, automated context for personal AI agents and users, i...

Olow304/memvid

Memvid is a video-based AI memory library that stores millions of text chunks in MP4 files with ultra-fast semantic search, eliminating the need for traditional databases and enabling portable, efficient AI memory management.

EverMind-AI/EverOS

EverOS is an open-source Python framework for self-evolving, portable, long-term memory for AI agents, supporting multimodal ingestion and local-first persistence with Markdown as the source of truth.

MemTensor/MemOS

MemOS is a Memory Operating System for LLMs and AI agents that unifies long-term memory management, offering a single API for structured, multi-modal memory with enterprise-grade optimizations, sig...