Havuz

Obsidian-powered daily logs, session logs, /prepforreset handoffs, and wiki janitor skills for AI agents.

Codex skill for building an Obsidian + ChatGPT sidebar workflow with vault-scoped MCP tools and ngrok remote access

A native iOS app for syncing your Obsidian vaults via git. Fast, simple, no fuss.

Obsidian plugin rendering the vault graph as an interactive 3D star map with Unity WebGL

A native live preview markdown editor for Mac

Local-first control plane for verifiable AI-assisted software engineering and Linux operations with structured knowledge substrate

Constantly-updated memory for your legal documents.

Open-source MCP server over a git-backed Obsidian vault. Single-user, self-host. Six tools, hybrid search, provenance/blame, auto-link disco

AI-managed personal knowledge base using Karpathy LLM Wiki Pattern. Obsidian vault with automated workflows for ingestion, compilation, Q&A,

Local knowledge base for AI agents (hermes plugin): hybrid search over your PDFs, DOCX, sites, YouTube and Obsidian; answers grounded strict

Telegram bot that saves YouTube Shorts to Notion or Obsidian using AI extraction. Self-hosted, Docker, modular LLM backends.

Self-hosted personal knowledge brain for Telegram, WhatsApp, n8n, Groq, and Obsidian. Save links, voice notes, and images; auto-summarize, c

Split-view reading for Obsidian — AI-generated summary cards with scroll-sync highlighting

Open-source agent skills for building scope-safe Markdown knowledge vaults with deterministic validation and research workflows.

Obsidian plugin: turn any note into a glassy Eisenhower matrix (urgent-important priority matrix) and organize your tasks as sticky notes.

Karpathy's LLM Wiki, built from your Claude Code sessions: a folder of markdown you own, Obsidian-native when you want it. Keeps what you de

Clone-and-go agent skills + a starter Obsidian vault for an AI-maintained personal wiki. Based on Karpathy's LLM Wiki pattern.

Offline tool that maps a Markdown/Obsidian vault and tells you which notes to fix first — center topics, orphans, noise, and a per-note next

WAKE.md for AI agents: compile project state so agents stop starting cold.

A visual style library that turns art movements, drawing styles, film looks and camera recipes into composable prompt layers. Obsidian + CLI

Evidence-grounded AI secretary for Claude Code and Codex, with frozen context, deterministic retrieval, bounded quality review, and explicit

Crow: build your second brain from the documents on your computer. Downloads for macOS, Windows and Linux.

Personalized top-conference recommendations, human-guided paper notes, and shareable research galleries that grow with your work.

Turn Instagram reels into a searchable content research library. Save, transcribe, and ask AI what hooks, stories, and CTAs made them work.

Karpathy-inspired LLM Wiki demo: AI agents compile raw sources into a persistent, self-linking Markdown knowledge base. The Agent writes. Th

Obsidian plugin adding highly customizable and native-feeling chart layout to Bases. Built with pure SVG and zero dependencies.

Local-first MCP server for Obsidian vaults — no plugins, no API keys, with schema-validated Bases (.base) support.

Yapay zekâ ekibini (Claude, Codex) ve Obsidian ikinci beynini tek ekrandan yöneten şifreli Windows uygulaması: onay kapısı, limit dolunca ka

OMI/Obsidian memory tooling (Open Knowledge Format) for AI agents: reproduce the integration on any machine, plus a local web app to view, e

LLM WIKI 知识工厂 — Reasonix Skill：端到端知识库构建流水线（查重清理→格式转换→LLM理解融合→Obsidian输出→持续维护）

Sistema Operativo de Memoria y Orquestación para Desarrollo con IA

Run Claude Code inside Obsidian with an interactive terminal, quick-ask modal, and a built-in MCP server for structured vault access.

amore (ah-my-openresearch) is opencode-based research workspace with personas, bundled skills, project lab contracts, and literature-wiki wo

CLI + MCP for agent context: a task layer over TickTick, Notion, GitHub, Obsidian & more (RRF retrieval, provenance, reviewed writes, undo)

A lightweight Personal OS using Claude + Obsidian to turn recurring friction into systems that actually work.

An Obsidian + GitHub template that digests your team's scattered chats, meetings, and documents into shared context that humans and AI read

A personal second brain for Claude Code — and a shared memory layer for mixed AI + human teams. Markdown vault + auto-capture + semantic sea

Retired

Graph + local semantic context for Obsidian, with guarded remote MCP access and edits from Codex, ChatGPT, Claude, and any MCP client.

The TUI-styled documentation template for your Obsidian vault. Built on Fumadocs + Next.js. Styled like a terminal. Read by AI agents.

Local-first personal knowledge base CLI — hybrid FTS + pgvector search, a GraphRAG entity graph, and LLM enrichment over your notes, transcr

Agent-friendly Markdown-to-PDF CLI with local PDF rendering and JSON diagnostics.

Sync & tag your ChatGPT/Claude exports into Obsidian using a local LLM. No cloud, no API keys.

Chat with your Obsidian (or git!) markdown on the go with your own private remote MCP Server

Zero-LLM incremental index + lazy semantic layer for knowledge vaults (markdown, HTML, PDF, images). One file, no dependencies, sub-second u

Local-first 3D space for flying through Obsidian-compatible Markdown vaults.

Hikari's curated English measured notes on local LLM systems (serving, specdec, training, steering).

Claude Code memory system — auto context injection, drift detection, compounding, FTS5/vector search, Obsidian vault export. Zero core deps.

Local-first, branch-aware long-term memory for Codex, backed by Obsidian.