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/Twin Gemini

Twin Gemini

volter · App

Twin Gemini is a twin of the Gemini Generative Language API, built to test applications that call it. It serves generateContent and streamGenerateContent, with streaming over Server-Sent Events. Answers come from a scenario you script, matching on the model, message text, tool results and more, or else from a labelled synthetic stub that can return text, schema-shaped JSON, a function call or a placeholder PNG. No model runs, and Google Search grounding is scripted rather than performed.

Written by ooruby from the README of @volter/twin-gemini 1.0.0.

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

Why it's useful

You can test code that calls the Gemini API against scripted answers instead of live model output.

What you could do with it

  1. 1Script a scenario that returns a function call when a request includes a given tool, and test your tool handling.
  2. 2Request a streamed reply over Server-Sent Events, then as a JSON array, and check how your client reads each.
  3. 3Ask for schema-shaped JSON and get a labelled synthetic answer to test your parsing.

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

TGappDeveloper 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
Data handling disclosed
finding
no statement of what it reads, writes or sends (README.md)

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

Gemini API twin (Protocol 3): generateContent and streamGenerateContent, answered by the World's scenario or a labeled synthetic stub; AI Studio API keys. Built on @volter/world-core.

Compare with

  • Node Llama Cppside by side
  • Anthropic Ai Sandbox Runtimeside by side
  • Ruvllmside 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 1.0.0, the file with digest sha512-SRRjoIP4GDyG0u4hHjLitqPtF5BzeW60VpY/SvN7HEyrNM6HItSZm1BkDLTsz7JbWj3+H+djnqtWdsYlGn2GNA==, 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 @volter/twin-gemini@1.0.0

Pinned to 1.0.0, 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
@volter/twin-gemini
Version read
1.0.0
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/volter-twin-gemini)](https://ooruby.com/market/volter-twin-gemini)

About this listing

Kind
App
Category
Developer tools
Pricing
Free
Sandbox
No
Hosted
No
Updated
2026-10-04
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 volter

See the storefront
SUagentDeveloper tools
5 findingsStatic scanned
It also talks to any OpenAI-compatible endpoint. You sign in by pasting an OpenRouter key and give it tasks from the command line, and native builds exist for macOS, Linux and Windows.

Supercode

volter
Free

Runs a coding agent in your terminal on OpenRouter models and continues Claude Code and Codex sessions.

42.2k installs/moMIT OR Apache-2.0
VZagentDeveloper tools
4 findingsStatic scanned
Its check command verifies once and exits non-zero on failure, for CI or pre-merge. Its loop command uses Stop hooks to hold your agent's turn until the work passes, within a capped number of iterations.

Volter Ztrack

volter
Free

Checks that each acceptance criterion an agent marks done cites a real commit and proof.

14.2k installs/moApache-2.0
TLappDeveloper tools
Clean scanStatic scanned
Events fold into a queryable store of traces, observations, sessions and scores that you can browse through the public API or a trace explorer. Requests use basic authentication, and unsupported operations fail with an error.

Twin Langfuse

volter
Free

Runs a local Langfuse API that the Langfuse SDK or an OpenTelemetry exporter can send traces to.

6.2k installs/moApache-2.0

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.