book-to-skill vs chroma
The two are close in size: 35.4k stars for book-to-skill, 29.5k for chroma. Over the days we have tracked them book-to-skill moved +14.8% and chroma +2.4%, so book-to-skill is growing faster right now.
book-to-skill leads on context depth. chroma does not take any axis by a clear margin.
Stars and commit dates come from our own daily tracking. The six axes are read off each project's documentation by our review pipeline, so they describe what a project says about itself, not what we measured in its code.
Where they stand today
Converts books and document collections into cross-agent, on-demand 'skills' with per-chapter files so agents answer from real content without dumping entire books into context.
- Stars
- 35.4k
- Tracked growth
- +14.8%
- Maturity
- ●●●●●
- Last commit
- 1d ago
- Language
- Python
- License
- MIT
- Cost to run
- Free, local processing; external model API costs apply
Provides a minimal, 4-function client API for fast in-memory prototyping plus an optional hosted Chroma Cloud for production-ready vector search.
- Stars
- 29.5k
- Tracked growth
- +2.4%
- Maturity
- ●●●●●
- Last commit
- 7h ago
- Language
- Rust
- License
- Apache-2.0
- Cost to run
- Free to self-host; optional Chroma Cloud hosted service
Six axes, head to head
Each axis runs 0 to 5. The label under a score is what that project's own docs claim, not a category average.
| Axis | book-to-skill | chroma |
|---|---|---|
Context depth How much of your codebase it sees before it answers: the open diff, the diff plus related files, or the whole repository. | ●●●●● Whole-skill access | ●●●●● No repo context |
Noise control How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only. | ●●●●● Validation & rules | ●●●●● Basic filters |
Customization How far it bends to your team: custom rules, prompts, style guides, per-path config. | ●●●●● Config file + options | ●●●●● Configurable API |
Privacy Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only. | ●●●●● Local processing | ●●●●● Runs locally |
Model freedom Whether you can point it at any provider, or it is wired to one. | ●●●●● BYO model | ●●●●● Bring-your-own models |
Setup ease What it takes to get a first useful run out of it. | ●●●●● One-command install | ●●●●● Quick start |
Which one to pick
Pick book-to-skill if…
Privacy-first — processes documents locally into compact, on-demand agent skills to avoid hallucination and reduce token/token-costs when querying.
- Context depth: Whole-skill access (5/5 against 1/5)
Pick chroma if…
Easy setup — pip install chromadb and use a simple 4-function API to run an in-memory vector DB for rapid prototyping, with an optional hosted cloud when you need it.
What people want from each one
virgiliojr94/book-to-skill
- PDF: `pdftotext -layout` interleaves columns on multi-column documents, and the word-based token estimate hides the 26x size blowup 👍 0
- [bug] Interrupted-run reuse accepts missing or corrupted extracted text 👍 0
- [bug] BeautifulSoup HTML/EPUB extraction inserts newlines inside inline headings and code tokens 👍 0
chroma-core/chroma
Hacker News: Chroma: Ubisoft's internal tool used to simulate color-blindness drew 231 points and 86 comments.
Questions people ask
Is book-to-skill better than chroma?
book-to-skill leads on context depth. chroma does not take any axis by a clear margin. book-to-skill is worth picking when privacy-first — processes documents locally into compact, on-demand agent skills to avoid hallucination and reduce token/token-costs when querying.
Which of book-to-skill and chroma keeps my code private?
book-to-skill: Local processing (5/5). chroma: Runs locally (5/5).
What does each one cost to run?
book-to-skill: Free, local processing; external model API costs apply. chroma: Free to self-host; optional Chroma Cloud hosted service.
Full profiles: virgiliojr94/book-to-skill and chroma-core/chroma. Everything else in RAG & retrieval.