{
  "markdown": "---\ntype: overview\ntitle: \"Cole Medin AI Knowledge Base\"\ndescription: \"An Open Knowledge Format (OKF) wiki mined from Cole Medin's entire long-form YouTube catalog, built to be dropped next to any project as agent-ready reference.\"\ntags: [readme, overview]\nupdated: 2026-07-21\n---\n\n# Cole Medin - AI Knowledge Base\n\nA synthesized, densely cross-linked knowledge base mined from [Cole Medin's](https://www.youtube.com/@ColeMedin) **entire long-form YouTube catalog** - agentic coding, AI engineering, RAG, harnesses, memory systems, and more. It is an [Open Knowledge Format](https://github.com/GoogleCloudPlatform/knowledge-catalog) (OKF v0.1) bundle and a Karpathy-style [LLM wiki](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f): plain markdown + YAML frontmatter, navigated by index and relative links, no database and no embeddings required.\n\n**The point:** drop this folder next to your project and any coding agent can answer questions from Cole's videos with citations back to the exact video and timestamp - zero integration, no RAG stack, no API keys.\n\n## What's inside\n\n- **`concepts/`** - the ideas, techniques, patterns, and mental models (the PIV loop, context engineering, agentic search, and so on), each synthesizing every video that discusses it.\n- **`entities/`** - the tools, people, and organizations (Claude Code, Archon, MCP, Anthropic, …).\n- **`sources/`** - one summary page per video, with provenance to the raw transcript.\n- **`raw/`** - the immutable, timestamped transcripts (the source of truth).\n- **`index.md`** - start here (after `SCHEMA.md`). The compiled wiki *is* the search index.\n\n## Use it with an agent (copy-paste)\n\nPoint your coding agent at this bundle with a prompt like:\n\n```\nUse the Cole Medin AI Knowledge Base as a reference:\n\n1. Clone it next to my project (skip if I already have it):\n   git clone https://github.com/coleam00/cole-medin-knowledge-base.git\n\n2. Read `cole-medin-knowledge-base/index.md`, then `cole-medin-knowledge-base/SCHEMA.md`.\n   This is an Open Knowledge Format (OKF) bundle - a linked wiki of concepts and entities\n   mined from Cole Medin's videos. Navigate it the OKF way: read the index, follow the\n   relative links into `concepts/`, `entities/`, and `sources/`, and open only the pages a\n   question needs. Do not load the whole folder.\n\n3. When I ask a question, answer from the knowledge base and cite the concept/entity pages\n   you used and the source video(s) they came from (each page ends with a `## Sources`\n   section listing the videos and timestamps). If something is not covered, tell me instead\n   of guessing.\n```\n\n## Build your own (from any YouTube channel)\n\nThree Claude Code skills are included that replicate the full pipeline - just point them at a channel. Each fetches transcripts using a different method, then walks you through the extract-canonicalize-write process described below.\n\n| Skill | Method | API Key | Cost | Best for |\n|-------|--------|---------|------|----------|\n| `/channel-to-kb` | pytubefix + youtube_transcript_api | None | Free | Quick setup, local machines |\n| `/channel-to-kb-ytdlp` | yt-dlp | None | Free | Most reliable, captures publish dates |\n| `/channel-to-kb-supadata` | Supadata API | Required | $17+/mo | No IP issues, AI fallback for uncaptioned videos |\n\n```bash\n# Example: build a KB from 3blue1brown's channel using yt-dlp\n/channel-to-kb-ytdlp @3blue1brown\n```\n\nEach skill fetches all transcripts as `raw/*.md` files, then guides Claude through the same pipeline used to build this bundle: extract concepts from each transcript, canonicalize (merge duplicates into single canonical pages), write cross-linked concept/entity/source pages, and validate with `lint.py`. The full pipeline reference is at `.claude/references/pipeline-guide.md`.\n\nFor small channels (under ~30 videos), the whole build fits in one Claude Code session. For larger channels, the skill batches the work and you can resume across sessions.\n\n## How it was built (reproducible)\n\n1. **Source.** Full transcripts for every long-form video are pulled from the source database and written as immutable `raw/<slug>.md` files (timestamped), plus `raw/manifest.json`.\n2. **Extract.** Each transcript is mined for the concepts and entities it teaches, with timestamped quotes.\n3. **Canonicalize.** All candidates are deduplicated into one taxonomy so each durable idea is a single page synthesizing every video that covers it (synthesis, not one-page-per-video).\n4. **Write & link.** Concept/entity/source pages are written and cross-linked with typed relationship headings.\n5. **Validate.** `python scripts/build_indexes.py` regenerates the indexes; `python lint.py` gates conformance, link integrity, index coverage, and orphans.\n\nFor the full story - the two-pass agent architecture, the tooling, and the validation results (citation integrity, adversarial QA, recall) - see [`docs/MAKING-OF.md`](docs/MAKING-OF.md) and [`tools/`](tools).\n\nSee [`SCHEMA.md`](SCHEMA.md) for the full contract and [`docs/ingestion-workflow.md`](docs/ingestion-workflow.md) for the step-by-step. Coverage and growth model are in [`roadmap.md`](roadmap.md).\n\n## License / provenance\n\nKnowledge is synthesized from publicly available YouTube videos by Cole Medin; each page cites its sources. Raw transcripts are included under `raw/` for provenance and auditability.\n",
  "bytes": 5369,
  "sha": "b133a56d63a88e70bc36a13757dbef448f1abc9381f757f0a4b8fc0bf416668b",
  "repo_slug": "coleam00/cole-medin-knowledge-base",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/okf_coleam00_cole_medin_knowledge_base_index_254d4caa/readme"
}