Look twice.Find the gem.

AI agents and MCP servers, each published with its source and what the checks found.

Marketplace

  • Everything
  • AI agents
  • Apps
  • MCP servers
  • Templates
  • What people want
  • What changed this week
  • The verification standard
  • The ooruby Index
  • Servers that publish no source
  • Reliability guides
  • What the catalogue holds
  • Sell here

Our library

  • Everything, in one place
  • Guides
  • Glossary
  • Calculators
  • Checklists and cheat sheets
  • Community

ooruby

  • Home
  • For teams
  • Site status
  • Company projects
  • RSS feed

Verification records what our published tests found on a specific version at a specific date. It is not a warranty, and it does not certify that software is free of defects.

AI agentsAppsMCP serversTemplatesWantedCommunityOur library
Sign inSell
Catalogue/Apps/Typesafe

Typesafe

ruvector · App

Typesafe takes one text and a batch of typed questions: a choice picks one of several options, a score places the text on a scale such as Calm, Irritated or Angry, and a noul rates a predicate from 0 to 1. Each answer carries a confidence, an abstain share for off-topic input and a receipt naming what produced it. It runs locally with a native core and a WebAssembly fallback, and its HTTP server accepts the System One request shape.

Written by ooruby from the README of @ruvector/typesafe 0.2.0.

Not claimed by its maker. Is this yours? Prove it and answer the findings

Why it's useful

You get typed, labelled decisions about text from a local component, with an abstain signal for input that fits no option.

What you could do with it

  1. 1Route a support message by asking it to choose between billing and fraud, and read the confidence returned.
  2. 2Score a message as Calm, Irritated or Angry and use the per-bucket probabilities in your own logic.
  3. 3Add a catch-all option so off-topic messages are flagged instead of forced onto the nearest answer.

Written from its documentation: what it says it can do, not what our checks found.

TYappDeveloper tools

Maintenance

Not measured

No release date is on record for this package yet. The nightly publisher check records one as it reaches each npm package, about once every ten nights.

Release activity only: it says nothing about quality or safety, and a finished small package can be fine without releases. How it is measured

Not yet tested
Command execution is bounded
inventory
node child_process (README.md:295)
An inventory of where the code starts another program, not a verdict on this row: whether each one runs a fixed program or whatever it is handed takes a reading by hand.
Licence and provenance
finding
no LICENCE file at the root (.)

Published because it was found. A finding is information about where the limits are, not a verdict that the software is unsafe.

What this does not cover

  • ·Everything. Treat it as you would software from anywhere else.

Receipt history: every signed receipt for every version of this listing, and what changed between them.

In its maker's words

Local typed decisions (choice / score / noul) over sentence embeddings — a ruvector-powered, self-optimizing alternative to typesafe.ai's System One API. Native (napi-rs) with a WASM fallback; no network, no per-token cost.

Compare with

  • Jev Swapside by side
  • Happyvertical AIside by side
  • Node Llama Cppside by side
Compare all 4

How far this has been checked

Static scanned

What it establishes
Its published package, or for a hosted server its source repository at a recorded commit, was read file by file, without running it, by every check in our current scan.
What it does not
How it behaves when it runs, or anything the scan does not read yet: several rubric checks, the repository's history, and compiled code in folders named dist or build. For a hosted server, that the endpoint runs the code that was read. The ooruby Index sets out exactly what was read.
Exactly what was read
Version 0.2.0, the file with digest sha512-oU+njNclrdU7wGOfhjCijnSf4vfJqpMqno60sKq+vVb+oUyfrRRIMrPLp0+dCLZgMRMpMahazKjcpl4fth1oRg==, as the registry publishes it. A published version cannot be replaced, so this names the same bytes for anyone who checks.
Authentication
Runs locally. No hosted endpoint is listed for this package. You run it on your own machine, so there is no endpoint of ours to authenticate against.
How the rungs work

Adding it

Run it with:

npx -y @ruvector/typesafe@0.2.0

Pinned to 0.2.0, which is the version the findings above were found in. Drop the version to take whatever is newest, and the report on this page stops describing what you installed.

Where this came from

Registry
npm
Package
@ruvector/typesafe
Version read
0.2.0
Resolved
2026-10-10
Open the source(opens in a new tab)

No build provenance published. The repository above is the one the publisher declared, and nothing links it to the package you would install. That is not a mark against this listing, since most packages are published this way, but it is a check nobody can run.

The badge, if this is your listing

It renders the current rung (static scanned) and links back here, where what that does and does not establish is one click away. It updates itself as the evidence deepens.

[![ooruby: static scanned](https://ooruby.com/api/badge/ruvector-typesafe)](https://ooruby.com/market/ruvector-typesafe)

About this listing

Kind
App
Category
Developer tools
Pricing
Free
Sandbox
No
Hosted
No
Updated
2026-10-08
Price
Free
Get it freeVisit maker
Rating
no reviews yet
0 want this so far
Sign in to vote

Sign in to watch this listing and hear when its version, rung or findings change.

More from ruvector

See the storefront
RUappDeveloper tools
5 findingsStatic scanned
Built in Rust with SIMD kernels. It also lists eviction policies for long contexts, a quantised embedding store, model download and upload through the HuggingFace Hub and adapter merging with TIES, DARE or SLERP.

Ruvllm

ruvector
Free

Runs GGUF language models in Node.js, with KV-cache compression, LoRA adapters and streamed output.

430.7k installs/moMIT OR Apache-2.0
RRappData & analytics
3 findingsStatic scanned
Built on WebAssembly with no server needed, plus graph neural network training, cosine, euclidean and dot-product search, and IndexedDB storage. A web dashboard runs queries live and includes demo simulations.

Ruvector Rvlite

ruvector
Free

Run a vector database inside the browser and query it with SQL, SPARQL or Cypher.

4.6k installs/moMIT OR Apache-2.0
PBappDeveloper tools
1 findingStatic scanned
A command line and SDK for a brain server that needs an API key. It can also start an MCP server for Claude Code, with tools to search, share, vote on, list and delete memories.

Pi Brain

ruvector
Free

Search and contribute to a shared brain of knowledge that AI sessions can look up and add to.

2.8k installs/moMIT

Similar apps

All apps
CCappDeveloper tools
4 findingsStatic scanned
Besides the terminal, you can use it in your IDE or tag Claude on GitHub. Anthropic collects feedback when you use it, including usage data such as code acceptance, conversation data and bug reports.

Claude Code

anthropic-ai
Free

Puts Claude in your terminal to understand your codebase, edit files and handle git workflows.

80.2M installs/moSEE LICENSE IN README.md
EWappDeveloper tools
2 findingsStatic scanned
Build a collection of providers and stream through it, registering every built-in provider or only the ones you use to keep bundle size down. Tool arguments are parsed as they stream in, and can be checked before a tool runs.

Earendil Works Pi AI

earendil-works
Free

Gives your app one API for streaming from many AI model providers, with typed and validated tools.

14.6M installs/moMIT
TOappDeveloper tools
1 findingStatic scanned
A JavaScript library with no dependencies and a bundled command line tool. It can also check text against a token limit, slice text by token position and split it into chunks.

Tokenx

johannschopplich
Free

Estimates how many tokens a text will use without loading a full tokeniser, from code or the shell.

5.8M installs/moMIT

Verification records what our published tests found on a specific version at a specific date. It is not a warranty, and it does not certify that software is free of defects.