PageIndex vs zvec-grep
PageIndex is much bigger: 38.5k stars against 3.9k. Over the days we have tracked them PageIndex moved +14% and zvec-grep +170.9%, so zvec-grep is growing faster right now.
zvec-grep leads on setup ease. PageIndex 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
Vectorless, reasoning-based hierarchical retrieval that builds a human-like table-of-contents tree for traceable, context-aware RAG without vector DBs or chunking.
- Stars
- 38.5k
- Tracked growth
- +14%
- Maturity
- ●●●●●
- Last commit
- 1d ago
- Language
- Python
- License
- MIT
- Cost to run
- Uses your LLM API key (e.g. OpenAI); cloud service may be paid.
Unifies ripgrep, BM25, and vector search into a local-first search layer that serves both humans and AI agents.
- Stars
- 3.9k
- Tracked growth
- +170.9%
- Maturity
- ●●●●●
- Last commit
- 22h ago
- Language
- Rust
- License
- Apache-2.0
- Cost to run
- Free local use; external models may require your API key.
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 | PageIndex | zvec-grep |
|---|---|---|
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-repo analysis | ●●●●● Whole-repo index |
Noise control How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only. | ●●●●● Basic filters/config | ●●●●● Ranked + filters |
Customization How far it bends to your team: custom rules, prompts, style guides, per-path config. | ●●●●● Config file options | ●●●●● Configurable options |
Privacy Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only. | ●●●●● Self-hostable | ●●●●● Fully local |
Model freedom Whether you can point it at any provider, or it is wired to one. | ●●●●● Bring-your-own | ●●●●● Bring-your-own-key |
Setup ease What it takes to get a first useful run out of it. | ●●●●● API key + install | ●●●●● One-command start |
Which one to pick
Pick PageIndex if…
Vectorless, reasoning-based retrieval — pick PageIndex when you need traceable, explainable, context-aware answers from long professional documents without a vector DB.
Pick zvec-grep if…
Privacy-first — local-by-default indexing and search that works for both CLI users and agent integrations with a single install.
- Setup ease: One-command start (5/5 against 3/5)
What people want from each one
VectifyAI/PageIndex
Hacker News: Show HN: PageIndex – Vectorless RAG drew 192 points and 128 comments.
zvec-ai/zvec-grep
Questions people ask
Is PageIndex better than zvec-grep?
zvec-grep leads on setup ease. PageIndex does not take any axis by a clear margin. PageIndex is worth picking when vectorless, reasoning-based retrieval — pick PageIndex when you need traceable, explainable, context-aware answers from long professional documents without a vector DB.
Which of PageIndex and zvec-grep keeps my code private?
PageIndex: Self-hostable (4/5). zvec-grep: Fully local (5/5).
What does each one cost to run?
PageIndex: Uses your LLM API key (e.g. OpenAI); cloud service may be paid.. zvec-grep: Free local use; external models may require your API key..
Full profiles: VectifyAI/PageIndex and zvec-ai/zvec-grep. Everything else in RAG & retrieval.