Tina Cook

I still don’t understand why people keep building a Claude second brain from scratch when these 10 repos already built the whole system They take in your sources, link them into a wiki, check every claim, and one of them runs fully on your own machine 01 obsidian-skills → Obsidian’s own CEO teaches Claude how Obsidian really works github.com/kepano/obsidian-s… 02 claude-obsidian → drop in any source and Claude reads it, links it and files it into one connected graph of plain Markdown you own github.com/AgriciDaniel/clau… 03 obsidian-second-brain → Claude Code remembers you between sessions, with 48 commands, all inside your Obsidian vault github.com/eugeniughelbur/ob… 04 karpathy-llm-wiki → one install line, then ingest, query with citations and lint, in Claude Code, Cursor, Codex or OpenCode github.com/Astro-Han/karpath… 05 second-brain → raw sources in, linked wiki pages out, browsed in Obsidian github.com/NicholasSpisak/se… 06 second-brain-os → the full kit: a 77-page guide, a starter vault, 18 skills, 72 commands and 6 subagents, four of them read-only github.com/undefined-ui/seco… 07 llm-wiki → two-layer memory: 10 to 20 rules Claude loads every session, 50 to 200 wiki pages pulled only when needed github.com/MehmetGoekce/llm-… 08 vouch → agents propose changes, you approve them, and a claim without a source is an error github.com/vouchdev/vouch 09 ai-second-brain → your ChatGPT and Claude history becomes a linked Obsidian vault, then a wiki github.com/charlie947/ai-sec… 10 LLM_Wiki_SecondBrain → the whole pipeline on a local model, no cloud API. 32 GB of RAM recommended github.com/DimitrisLianos/LL…