Graybox

Obsidian is a note-taking and personal knowledge management application by Obsidian.md that stores notes as local Markdown files. It provides features for linking notes (backlinks), a graph view, and a plugin system for extensibility across desktop and mobile.

gbrain is a hosted, cloud-based AI agent with persistent, long-term memory that adapts to a user’s preferences and way of thinking. It provides built-in skills for personal use and shared “brains” that support collaboration within teams and organizations.

NoteDiscovery is a lightweight, self-hosted knowledge-base and note-taking application developed by Gamosoft. It stores notes as plain Markdown files in folders on the user's server and provides search, navigation, graph views of connected notes, an outline panel, favorites, themes, plugins, LaTeX/MathJax, HTML export, printing, responsive desktop, tablet, and mobile interfaces, and an in-app drawing editor that saves sketches as PNG files alongside notes. The application serves its browser libraries locally without requiring a CDN, allowing operation on air-gapped networks. It can be deployed with optional password authentication and Docker, and includes a built-in Model Context Protocol (MCP) server for compatible assistants such as Claude and Cursor. Through the MCP integration, assistants can search, create, edit, move, tag, and append to notes and explore connections between them.

QMD is an on-device command-line search engine for Markdown notes, meeting transcripts, documentation, knowledge bases, and other organized information. It combines BM25 full-text search, vector semantic search, and LLM reranking locally through node-llama-cpp and GGUF models. Its hybrid query pipeline expands the original query into lexical, vector, and HyDE variants, routes them to keyword or vector search, combines the results with Reciprocal Rank Fusion, and applies an LLM reranker to produce final ranked results. Collections can be indexed and enriched with hierarchical context; documents can be retrieved individually or in batches, and JSON and file-oriented output formats support agent workflows. QMD also exposes query, retrieval, batch retrieval, and index-status operations through an MCP server.

agent-memory is a local-first, agent-agnostic long-term memory runtime for AI agents. It stores memories as plain Markdown files, with a rebuildable SQLite index used as a cache rather than the source of truth. Conversation-boundary hooks trigger writes, while an independent sleep-time Manage pass consolidates, ages, and forgets memories by value; unattended deletion is limited to proposals that require confirmation, and superseded or archived material remains available. The runtime provides three recall paths: deterministic MEMORY.md injection at session start, BM25 search with progressive disclosure, and direct access through the store's directory tree using tools such as ls and grep. Memory records use frontmatter for names, abstracts, status, timestamps, links, weights, and provenance, with free-form Markdown bodies. Its CLI, MCP server, and host-agent hooks share the same validation, hash-diff, and reindexing path, and it can be used by agents that run shell commands, including Claude Code and Codex CLI. The repository documents a Python 3.12-or-later setup using uv, commands for initialization, recording, recall, rebuilding, sleep-time consolidation, and proposal approval, plus host setup for Claude Code and Codex. It does not include an LLM client; reasoning is delegated to the host agent's CLI, so the library requires no separate model keys or billing surface.