cd /news/ai-tools/z-local-first-search-layer-for-human… · home topics ai-tools article
[ARTICLE · art-119438] src=github.com ↗ pub= topic=ai-tools verified=true sentiment=↑ positive

Z: Local-first search layer for humans and agents

Zvec AI released zg (zvec-grep), a local-first search tool unifying ripgrep, BM25, and vector search behind a single interface for humans and AI agents, requiring Node.js 22 or newer and installable via npm. The tool indexes files locally by default, supports multi-format search, and integrates with OpenCode, enabling agents to retrieve ranked, source-linked evidence with fewer tokens, as demonstrated in a Sherlock Holmes benchmark where Claude Code with Claude Opus 5 used zg to answer a query about unseen creature marks.

read4 min views1 publishedSep 2, 2026
Z: Local-first search layer for humans and agents
Image: Michielbdejong (auto-discovered)

English | 中文

Know the words—or don’t. Just zg.

The local-first search layer for humans and agents.

🎬 Tour |

💫|

Features🚀|

Try it yourself📚|

Docs📊|

Benchmarks🤝

Community****zg (z vec-g rep) unifies ripgrep, BM25, and vector search behind one local-first interface. Use it directly from the terminal, or let your agent use it for you.

Ready for humans and agents— install once, index once, then use the same workspace from the CLI or your agent on macOS, Linux, and Windows.** Search beyond keywords**— discover by meaning, rank by relevance, then verify with exact text or regex when needed.** Multi-format search**— search source code, documents, and structured data while preserving useful structure and source locations.** Less searching, less context**— ranked, source-linked results surface the right evidence with fewer tool calls, fewer tokens, and less noise.** Local by default**— files, indexes, and local models stay on your machine; remote embeddings receive data only with your permission.

npm install -g @zvec/zvec-grep

mkdir zg-mystery && cd zg-mystery
curl --retry 3 --retry-all-errors --progress-bar -fL \
  -o alice-in-wonderland.txt https://raw.githubusercontent.com/GITenberg/Alice-s-Adventures-in-Wonderland_11/master/11.txt \
  -o sherlock-holmes.txt https://raw.githubusercontent.com/GITenberg/The-Memoirs-of-Sherlock-Holmes_834/master/834.txt

zg index --embedding local/potion-retrieval-32m

With OpenCode configured:

zg install --target opencode --yes
opencode models
opencode run --model opencode/nemotron-3-ultra-free \
  "An unseen creature left a few marks. What did the detective infer? Cite local evidence."

Free model availability can change. Check opencode models

and replace the example model with one that is currently available in your environment.

OpenCode chooses zg on its own—the prompt does not name a tool.

See the full agent run and answer

⚙ zvec_grep_zvec_grep_search {"root":".../zg-mystery","query":"An unseen creature left a few marks. What did the detective infer?","fts":["marks","unseen creature","inferred","detective"],"fuse":true}
→ Read sherlock-holmes.txt [offset=5440, limit=120]

Answer:
The detective is Sherlock Holmes in *The Adventure of the Crooked Man*.
From the animal's foot-marks, he inferred:

- It was not a dog, cat, monkey, or other familiar creature: its print had
  five foot-pads, long nails, and was nearly as large as a dessert-spoon
  (sherlock-holmes.txt:5479-5486).
- It had a long body and very short legs: nearly two feet long, but with a
  stride of only about three inches (sherlock-holmes.txt:5497-5502).
- It was carnivorous because it climbed the curtain toward a canary's cage
  (sherlock-holmes.txt:5509-5510).
- It was probably from the weasel or stoat tribe, though unusually large
  (sherlock-holmes.txt:5514-5516).

Holmes also inferred that a man entered through the window with it and later
left with the key (sherlock-holmes.txt:5464-5470, 5527-5528).

Search the same bookshelf directly, without an agent:

zg query --human "An unseen creature left a few marks. What did the detective infer?" --limit 3

zg returns the relevant passages from sherlock-holmes.txt

, ranked ahead of alice-in-wonderland.txt

.

Each benchmark uses paired A/B runs with tasks, agent/model, prompt, environment, and limits held constant; only zg access and usage guidance differ.

See the benchmark documentation for full results and reproduction details.

SWE-QA-Bench uses Claude Code with Claude Opus 5 at high reasoning effort; BrowseComp-Plus uses Codex gpt-5.6-sol at medium reasoning effort. Both zg profiles use Qwen3.7 Text Embedding.

Why it helps: semantic discovery narrows the search space, ranked lexical retrieval anchors exact identifiers, and compact evidence reduces broad scans, repeated tool calls, and model context.Why it generalizes: the same retrieval loop works across domains—code is indexed with symbols, signatures, and breadcrumbs, while prose is retrieved as focused sections and chunks.

| |

the task asks how AST node handling separates annotated and non-annotated attribute initialization. Symbol-aware retrieval is useful because the architectural entry point is not known in advance.Pylint— Python static analysis:the task tracesMatplotlib— plotting and rendering:FontInfo

and font selection through multiple math-text rendering stages. Ranked semantic and lexical evidence helps reconstruct the cross-file data and control flow.the task connects username uniqueness, ORM transactions, and formset bulk operations. Compact ranked evidence brings the distributed design rationale together.Django— web framework:

Repository questions

Repository Question type Question
pylint-dev/pylint
What Architecture exploration
What is the architectural pattern that distinguishes type-annotated from non-annotated instance attribute initialization using AST node type separation?
matplotlib/matplotlib
Where Data / Control-flow
Where does the FontInfo NamedTuple propagate font metrics and glyph data through the mathematical text rendering pipeline, and what control flow determines whether the postscript_name or the FT2Font object is used at different stages of character rendering?
django/django
Why Design rationale
Why does the User model's unique constraint on the username field interact with Django's ORM transaction handling, and what cascading effects would occur if this constraint were removed on an existing database with formset-based bulk operations?

zg works best when evidence spans files or modules and the target location is unknown, especially for call-chain, data-flow, and architectural questions. Since agents decide when and how to use it, results vary by model and run; repeated-run averages are more reliable.

Guide What you can do

CLI guideMCP guideRetrieval pipelineArchitectureServer and execution modesEmbedding modelsRoadmapCommunity contributions are always welcome—bug fixes, features, and documentation improvements all help make zvec-grep better.

Check out our Contributing Guide to get started!

── more in #ai-tools 4 stories · sorted by recency
── more on @zvec ai 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/z-local-first-search…] indexed:0 read:4min 2026-09-02 ·