#obsidian

The knowledge compiler. Raw sources in, interlinked wiki out. Inspired by Karpathy's LLM Wiki pattern.

AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs, papers, images, or videos into a queryable knowledge graph. App code + database schema + infrastructure in one graph.

Hybrid search over your Obsidian vault – CLI and MCP server

Convert your data to Markdown files you can use in Obsidian. Works with Apple Notes, OneNote, Evernote, Notion, Google Keep, and many other formats.

Standalone MCP server for Obsidian vaults — hybrid search, structured memory, tasks, and full vault access for any AI agent

Persistent semantic memory for AI agents — 100% local on Apple Silicon (MLX) or Linux/Ubuntu (CPU). Markdown source of truth, sqlite-vec + BM25 hybrid search, a codegraph-backed knowledge graph, MCP server + CLI. No cloud, no keys.

Persistent memory for AI agents

Everything about note management. All in Zotero.

Long-term, cross-project memory for AI coding agents. Your own Obsidian vault as the source of truth. Daemonless and without opaque databases, your memory belongs to you.

Multi-project agent orchestration for Claude Code. One command session controls everything.

Obsidian Turbocharged — governed, agent-ready Obsidian MCP server. 141 tools across 31 domains, multi-vault native, pluggable embeddings. TypeScript + Rust. AGPL-3.0-only.

Headless client for Obsidian Sync. Sync your vaults from the command line without the desktop app.

该仓库未发布描述。

Turn YouTube, websites, and arXiv papers into a structured, reusable corpus of insights, syntheses, and reports.

A local-first CLI that makes your Obsidian vault searchable and AI- Agents queryable with semantic search and hidden connections. 100% local, no servers.