Sno Station
Sno Station은 AI 에이전트를 하나의 팀으로 묶는 오픈소스 워크스테이션으로, 로컬 머신에서 에이전트 협업을 가능하게 함
AI 엔지니어링·스타트업·투자 팟캐스트에서 배운 내용을 주제별로 정리하고, 모든 주장에 해당 에피소드와 발표자를 링크합니다
What I learned from AI engineering, startup and investing podcasts, synthesized by topic across episodes, with every claim linked to its episode and speaker.
플러그인HTML · PythonGitHub @HagaiHen온라인운영자 미확인
써 보셨어요? 한 번만 눌러 주세요. 로그인은 필요 없어요.
개인 계정의 공개 저장소 소유자는 GitHub로 로그인해 운영자를 확인하고 소개를 직접 관리할 수 있습니다. 관리자 승인은 필요하지 않습니다.
로그인한 뒤 확인 파일을 만들어 이 저장소의 기본 브랜치에 30분 안에 커밋해 주세요. 다른 브랜치나 포크의 파일은 인정하지 않습니다. 파일을 올린 뒤 아래에서 확인하면 관리자 승인 없이 관리할 수 있습니다. 자격을 유지하려면 파일을 남겨 두세요.
로그인이 필요하면 로그인 화면으로 이동합니다. 로그인 후 이곳으로 돌아와 원하는 확인 버튼을 다시 눌러 주세요.
프로젝트 폴더에서 /nomorevibe verify를 실행하면 소유권을 확인하고 소개를 직접 관리할 수 있습니다.
1분 만에 확인하기Claude Code plugin that turns the podcasts you listen to on Spotify into a cited LLM wiki: one page per topic, every claim linked to its episode.
저장소 README에서 가져옴
README 전체를 불러오는 중입니다. 아래는 저장된 발췌입니다.
A Claude Code plugin that turns the podcasts you finish on Spotify into a wiki you can learn from: one page per topic, synthesized across every episode that touched it, every claim linked to its episode, disagreements between guests kept side by side.
You stop remembering an episode and start knowing a topic. A Karpathy-style LLM wiki, written and maintained by Claude Code.
Browse the live wiki → · Try the demo · How it works
Click for the full video with sound.README 전문 보기 ↗A Claude Code plugin that turns the podcasts you finish on Spotify into a wiki you can learn from: one page per topic, synthesized across every episode that touched it, every claim linked to its episode, disagreements between guests kept side by side.
You stop remembering an episode and start knowing a topic. A Karpathy-style LLM wiki, written and maintained by Claude Code.
Browse the live wiki → · Try the demo · How it works
Click for the full 62s video.
In Claude Code:
/plugin marketplace add HagaiHen/podcast-wiki
/plugin install podcast-wiki@podcast-wiki
/podcast-wiki:demo in an empty folder. In about a minute it builds a small wiki from 3 sample episodes, with no Spotify needed./podcast-wiki:setup in an empty folder. It copies the tools, creates wiki/, and walks you through the Spotify login. After that, /podcast-wiki:ingest-podcasts builds your wiki.Requires macOS on Apple Silicon (for local Whisper), uv, ffmpeg, a Spotify account and Claude Code. The demo needs only Claude Code.
Spotify (episodes I've heard)
│ tools/spotify_mcp.py
▼
raw/<show>/<date>-<slug>.md ← transcript: published → Whisper → episode description
│ tools/fetch_transcript.py
▼
Claude Code follows the procedure in CLAUDE.md
▼
wiki/ concepts · hubs · episodes · people · shows · takeaways
Hebrew episodes are translated to English during synthesis.
wiki/index.md | Every page, grouped by domain. Start here. |
wiki/concepts/ | One topic each (e.g. harness engineering, LLM evals, index investing). |
wiki/hubs/ | Domain overviews: AI engineering, investing, knowledge management. |
wiki/takeaways/to-try.md | Actionable checklist, grouped by hub. |
wiki/takeaways/recommendations.md | Books, tools and people worth following. |
wiki/episodes/, wiki/people/, wiki/shows/ | Short source notes that the concepts link back to. |
The wiki is plain Markdown with Obsidian wikilinks ([[concepts/zone-2-training]]), so it opens as an Obsidian vault with a working graph view.
Note:
raw/(the full transcripts) is kept local and is not in this repo. Those transcripts are the podcasters' content; the wiki is a synthesis in my own words, linking back to each episode on Spotify.
Requires macOS on Apple Silicon (for mlx-whisper), uv, ffmpeg, and Claude Code.
http://127.0.0.1:8888/callback.cp .env.example .env and set SPOTIFY_CLIENT_ID. No client secret is needed because the login uses PKCE.uv run tools/spotify_mcp.py --auth to log in to Spotify once..mcp.json to your checkout./ingest-podcasts.| Command | What it does |
|---|---|
/ingest-podcasts | Full pipeline: list heard episodes → fetch text → update the wiki → commit → push. |
/lint-wiki | Health check: broken links, orphans, drift between pages; fixes what it finds. |
/dream | Consolidates Claude's project memory and merges duplicate concept pages. |
uv run tools/fetch_transcript.py --pending | Raw files not yet in the wiki. |
uv run tools/lint_wiki.py | Mechanical wiki checks only. |
Unattended: tools/scheduled_ingest.sh runs the pipeline headless. tools/com.user.podcast-wiki.plist is a launchd job that runs it every 6 hours; fix its paths, copy it to ~/Library/LaunchAgents/, and launchctl load it. Because the headless Claude reads untrusted transcripts, it may only write inside wiki/ and runs no git itself. The script commits and pushes afterwards.
CLAUDE.md holds the conventions, page templates and the step-by-step wiki update procedure Claude follows.