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/Templates/Starter Foundry

Starter Foundry

tangle-network · Template

Starter Foundry is a deterministic scaffold engine for AI coding agents: it routes a plain-language prompt to a project structure, writes the files and hands the agent its next steps. Its versioned registry combines base project types with feature layers, swappable infrastructure such as database, auth, payments and queues, and chain or protocol presets. Each stage works as a command or a TypeScript library export, so you can stop at a spec, a file tree or a full plan.

Written by ooruby from the README of @tangle-network/starter-foundry 0.13.5.

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

Why it's useful

Your coding agent starts from real project files and a list of next steps instead of a blank directory.

What you could do with it

  1. 1Describe a realtime chat app with auth and get a scaffold plus build plan in the current folder.
  2. 2Preview which project family and layers a prompt routes to before any files are written.
  3. 3Embed the planner and composer in your own product to give its coding agent a starting project.

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

SFtemplateDeveloper 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
eval (registry/layers/framework/lora-training/files/infer.py:75)
node child_process (registry/layers/capability/agent-eval/files/tests/eval/run-eval.mjs:28)
eval (registry/layers/agent-eval/trace-multi-turn/files/src/eval/trace/README.md:9)
eval (registry/layers/agent-eval/redteam/files/src/eval/redteam/README.md:52)
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.

Corrected after a reading by hand on 2026-10-10

  • No shipped credentials: the automated note “The scan matched 6 credential-shaped strings in the published files. Location withheld pending disclosure to the maker.” was withdrawn. Test values in a personal data detector's tests, among them AWS's documented example key and a key block cut short after its first line, and two setup instructions that say where a token goes.
How it was read

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

In its maker's words

Deterministic project scaffold engine for AI coding platforms

Compare with

  • Openuidev CLIside by side
  • Create Agent Appside by side
  • Create Llmside 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 0.13.5, the file with digest sha512-z/Ri57RB+dH2vY6TsjVBR+sgRtAdFOjNlJ/wsu/4kl3wRJSRpV8/JhLxrSHwEkb+WC0FyIA4gFER6BxRVz9Wsg==, 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 @tangle-network/starter-foundry@0.13.5

Pinned to 0.13.5, 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
@tangle-network/starter-foundry
Version read
0.13.5
Resolved
2026-10-09
Open the source(opens in a new tab)

Built from source, attested

npm publishes a signed statement that this exact package was built from the repository below, at this commit. It is verifiable without taking our word for it.

Repository
github.com/tangle-network/starter-foundry
Commit
e26a65e1a6d4
Built by
github.com/actions/runner/github-hosted
Registry publish attestation
signed by npm · 2026-10-10
Checked
2026-10-10

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/tangle-network-starter-foundry)](https://ooruby.com/market/tangle-network-starter-foundry)

About this listing

Kind
Template
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 tangle-network

See the storefront
CAtemplateDeveloper tools
1 findingStatic scanned
Builds the project on Tangle's agent-app package and leaves customisation notes to follow. Type checking and tests are there to run before you change anything, and the chat-first option points to a shared workspace composition.

Create Agent App

tangle-network
Free

Scaffolds a new Tangle agent application with either a tool loop or a complete chat interface.

13.5k installs/moMIT
AAagentDeveloper tools
2 findingsStatic scanned
Agents send proposals, follow-ups, citations and UI to your app as validated tool calls over HTTP, MCP or the runtime. Buffered turns let a reconnecting browser replay what it missed.

Agent App

tangle-network
Free

Supplies the chat routes, tool loop, approvals and billing pieces for agent apps on the Tangle stack.

42.5k installs/moMIT

Similar templates

All templates
OPtemplateDeveloper tools
Clean scanStatic scanned
Pick the OpenUI Cloud template with hosted models, or a self-hosted one using your own OpenAI-compatible key, then add a LangGraph, Vercel AI SDK or Vercel Eve backend if you want. It can also deploy the project to Vercel.

Openuidev CLI

openuidev
Free

Scaffolds OpenUI agent apps, mints Cloud API keys and turns component libraries into model prompts.

45.8k installs/moMIT
CMtemplateDeveloper tools
1 findingStatic scanned
Runs once as a project generator, so there is nothing to install first. Its interactive setup asks where to create the project and covers the Mastra directory, example agents, model provider and optional development tools.

Create Mastra

abhiaiyer
Free

Creates a new Mastra app with one command and helps you set up example agents and a model provider.

27.4k installs/moApache-2.0
CLtemplateDeveloper tools
Clean scanStatic scanned
Pick a template sized from about one million to one billion parameters. The project includes tokenizer training, checkpoints, TensorBoard, a live dashboard and deployment scripts.

Create Llm

theanikrtgiri
Free

Creates a PyTorch project for training your own small language model, from tokenizer to chat.

5.4k 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.