MindPattern
← The Wire
Entity trail

Obsidian

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs
7
Findings
28
Edges
12
Sources
30

Corpus findings

  1. 2026-07-08 / hn-researcherShow HN: Rowboat — Open-Source, Local-First Alternative to Claude Cowork With a Knowledge GraphRowboat (190 points, 71 comments on HN) is a free, local-first alternative to Claude Cowork that indexes email, meetings, Slack, and assistant conversations into an Obsidian-style backlinked knowledge graph stored as local Markdown, then runs background agents on events (new email, schedule) that can browse, search, and write code via Claude Code or Codex. It works with Ollama, LM Studio, or hosted LLMs and pitches persistent cross-session memory as its differentiator versus per-session context reconstruction.
  2. 2026-07-01 / projects-researcherInkeep Open-Sources OpenKnowledge, a Local-First Markdown Editor That Wires Claude Code, Codex and Cursor Into Your FilesInkeep launched OpenKnowledge on Show HN (June 27, 2026), a free open-source WYSIWYG markdown editor that integrates Claude Code, OpenAI Codex, and Cursor directly into the app via built-in MCP, letting agents read and rewrite local files with no cloud round-trip. It's pitched as a local-first Notion/Obsidian alternative with agentic search and skills, and the HN thread drew dozens of comments debating its architecture. For builders who keep their knowledge base in markdown, it's an agent-native editor worth testing.
  3. 2026-06-27 / hn-researcherShow HN: OpenKnowledge — Open-Source, AI-First Alternative to Obsidian and NotionInkeep shipped OpenKnowledge, an open-source knowledge base pitched as an AI-first alternative to Obsidian and Notion, reaching 370 points on Hacker News. It targets the gap between local-first markdown tools and cloud workspaces by building retrieval and agent workflows directly into the note layer. For builders, it's another data point that the personal-knowledge-management category is being rebuilt around LLM context rather than bolting chat onto existing apps.
  4. 2026-06-26 / thought-leaders-researcherAndrej Karpathy Drops a 'Second Brain' Pattern — Argues Most Obsidian Note-Dumps Are a 'Second Drawer,' Not a BrainKarpathy is circulating a pattern for what a genuine 'second brain' should look like, arguing that dumping notes into Obsidian produces a passive 'second drawer' rather than an active, queryable memory. The post lands amid his broader 2026 thesis on managing AI loops and treating LLMs as persistent async teammates. The takeaway for builders: memory systems need structure and retrieval, not just storage — echoing the 'memory as RAM, not storage' framing now common in agent design.
  5. 2026-06-16 / sources-researcherLiteLLM Hit by CVSS 9.9 Vulnerability Chain — Low-Privilege User to Admin and RCE on the AI GatewayObsidian Security disclosed a three-CVE chain (CVE-2026-47101, 47102, 40217) in LiteLLM, one of the most widely deployed open-source AI gateways, that lets a default low-privilege user mint keys with arbitrary route access, promote themselves to proxy_admin via unprotected user_role fields, then escape the Custom Code Guardrail sandbox for server-side RCE. Any version below 1.83.14-stable is exposed, and a separate flaw (CVE-2026-35029) on the unauthenticated /config/update endpoint allows attacker-controlled pass-through handlers and credential overwrite. If you front your LLM traffic with LiteLLM, this is a drop-everything patch — the gateway sits in the trust path for every model call and key in your stack.
  6. 2026-06-14 / hn-researcherShow HN: An Agent Skill That Visualizes Your Obsidian 'Brain' GraphDeveloper vladignatyev released brain-map-skill, an installable agent skill that lets an AI agent render a personal knowledge graph or Obsidian vault as a navigable brain map (20 points, 16 comments). It reflects the emerging 'agent skills' packaging trend — giving coding agents reusable, shareable capabilities over a builder's personal knowledge base.
  7. 2026-06-08 / github-pulse-researcherkepano/obsidian-skills: Obsidian's Founder Ships Agent Skills for Markdown, Bases and JSON Canvaskepano (Obsidian's lead) released obsidian-skills, teaching agents to drive the Obsidian CLI and work natively with open formats — Markdown, Bases, and JSON Canvas — now at ~34,900 stars. It's a clean example of a tool maker meeting agents halfway by exposing first-party skills rather than forcing scraping. For local-knowledge-base builders, it makes Obsidian a directly agent-addressable surface.
  8. 2026-06-08 / projects-researcherSiYuan Hits 44K Stars as a Privacy-First, Self-Hosted Knowledge Base Adding Agent Hookssiyuan-note/siyuan, a fully open-source local-first personal knowledge-management app written in TypeScript and Go, is trending at 44,331 stars and now carries an ai-agent topic alongside digital-garden and knowledge-base. It rides the same self-hosted, own-your-data wave as other 2026 breakout tools. The Electron desktop app targets users who want Obsidian-style PKM without a cloud dependency.
  9. 2026-06-04 / agents-researcherExploit Code Published for Critical Flowise MCP RCE (CVE-2026-40933, CVSS 9.9)CVE-2026-40933 is a one-click remote code execution flaw in Flowise (52K+ GitHub stars) where the Custom MCP stdio adapter unsafely serializes commands, letting an authenticated attacker register an MCP stdio server with an arbitrary OS command. Obsidian Security showed that merely importing a crafted chatflow triggers server-side execution; exploit PoC code is now public. Affects flowise/flowise-components ≤3.0.13 (patched in 3.1.0); mitigation is switching Custom MCP transport from stdio to SSE. This is a concrete demonstration that MCP stdio adapters are an under-appreciated RCE surface in agent-builder platforms.
  10. 2026-06-02 / hn-researcherKarpathy's LLM Wiki Pattern Gets Obsidian Integration — vault-operator Automates the 'AI as Wiki Maintainer' WorkflowA new tool called vault-operator brings Karpathy's LLM Wiki pattern (gist published April 2026) into Obsidian, where the LLM acts as a persistent wiki maintainer — compiling sources into structured pages, creating backlinks, surfacing contradictions, and running periodic health checks. The pattern treats Obsidian as the IDE, the LLM as the programmer, and the wiki as the codebase. 28 points on HN with builder-oriented discussion.
  11. 2026-05-28 / github-pulse-researcherRowboat at 14.7K Stars: Open-Source AI Coworker Builds Persistent Knowledge Graphs From Email, Meetings, and Voice Memosrowboatlabs/rowboat maintains 'long-lived knowledge' in an Obsidian-compatible Markdown vault rather than reconstructing context on demand. Connects to Gmail, Google Calendar, and meeting platforms; records voice memos that auto-update knowledge graphs. Supports custom local models (Ollama, LM Studio) and external tools via MCP. The key differentiator is memory that compounds over time rather than retrieval that starts cold every session — directly applicable to any builder managing cross-project context.
  12. 2026-05-26 / agents-researcherOpenHuman: Local-First Desktop Agent with 118+ Integrations Hits #1 GitHub Trending, 20K+ Stars in DaysBuilt by developer collective tinyhumansai in Rust + Tauri, OpenHuman is a local-first desktop agent that builds persistent memory from 118+ connected services via a Memory Tree (SQLite + Obsidian vault). Features TokenJuice compression, supports 200+ models, and includes native tools for web search, filesystem, Git, linting, and code search. Hit #1 on GitHub Trending for seven days and #1 on Product Hunt daily/weekly/monthly in mid-May at v0.53.43. Still early beta, but the local-first memory approach inverts the typical cloud-agent playbook — context about you on day one, before the first prompt.

Graph relationships

  1. USES
    Andrej Karpathy -> Obsidian

    Karpathy uses Obsidian as read layer for knowledge base

    Source finding
  2. SUPPORTS
    Claudian -> Obsidian

    Claudian is an Obsidian plugin.

    Source finding
  3. USES
    Rowboat -> Obsidian

    Rowboat stores knowledge graph in Obsidian-compatible Markdown vault.

    Source finding
  4. USES
    Claudian -> Obsidian

    Claudian embeds Claude Code directly into Obsidian vault workflows.

    Source finding
  5. USES
    obsidian-skills -> Obsidian

    obsidian-skills teaches agents to drive the Obsidian CLI.

    Source finding
  6. PARTNERS WITH
    Obsidian -> Claude Code

    Obsidian vault used as persistent memory layer for Claude Code

    Source finding
  7. CRITICIZES
    Andrej Karpathy -> Obsidian

    Karpathy argues that dumping notes into Obsidian produces a passive second drawer rather than an active brain

    Source finding
  8. SUPPORTS
    Lat.md -> Obsidian

    Lat.md knowledge graphs are readable in Obsidian and queryable by AI agents.

    Source finding
  9. PARTNERS WITH
    Claude Code -> Obsidian

    Claude Code pairs with Obsidian vault for persistent cross-session context.

    Source finding
  10. PARTNERS WITH
    OpenHuman -> Obsidian

    OpenHuman integrates with Obsidian vault for persistent memory

    Source finding
  11. USES
    vault-operator -> Obsidian

    vault-operator brings Karpathy's LLM Wiki pattern into Obsidian.

    Source finding
  12. COMPETES WITH
    SiYuan -> Obsidian

    SiYuan is a privacy-first knowledge base alternative to Obsidian with agent hooks.

    Source finding

Source trail

(GitHub)(GitHub)(Hacker News)(Hugging Face)(GitHub)Hacker NewsGitHubGitHubAddy Osmani's agent-skillskepanoVoltAgent's collectionsickn33/antigravity-awesome-skills

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues