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/Codex Forge

Codex Forge

ytechai · App

Codex Forge is a local Node.js gateway for Codex Desktop and the Codex command line. It accepts the Responses API requests Codex makes and routes each one to OpenAI chat completions, Anthropic messages, another OpenAI-style chat endpoint or, when a valid token is present, the ChatGPT Codex backend. Models from providers such as OpenAI, Anthropic, DeepSeek, Gemini and OpenRouter then appear in the normal Codex picker. It suits people who want their own provider keys inside Codex.

Written by ooruby from the README of @ytechai/codex-forge 0.1.45.

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

Why it's useful

You can keep the native Codex editor and agent experience while choosing which model provider answers each request.

What you could do with it

  1. 1Add a DeepSeek or other OpenAI-style model to the Codex picker by listing its provider, protocol and your key.
  2. 2Run the server on another machine on your network and manage Codex models from the command line where Codex is installed.
  3. 3Turn on the optional Auto router so each task goes to a model chosen by a classifier model.

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

CFappInfrastructure

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

Local all-model BYOK configuration forge for Codex Desktop and CLI. Single install supports both server mode and CLI tool mode.

Compare with

  • Omnirouteside by side
  • AI Ctrfside by side
  • Gatewayside 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 0.1.45, the file with digest sha512-LXOuxQZwxGFs2KuF0mUEIZQjJzSLxM7w2HAJZBb1GlUKZ4PXiS8S8kj0dAFNsQcQP3ndJ4SxJA2INj/j60/u8A==, 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 -p @ytechai/codex-forge@0.1.45 codex-forge-cli

Pinned to 0.1.45, 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
@ytechai/codex-forge
Version read
0.1.45
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/ytechai-codex-forge)](https://ooruby.com/market/ytechai-codex-forge)

About this listing

Kind
App
Category
Infrastructure
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 ytechai

See the storefront
VCappInfrastructure
Clean scanStatic scanned
Runs as a local service with a route for each provider. It accepts OpenAI Chat Completions, OpenAI Responses and Anthropic Messages requests, lists models, and can start automatically at login.

Vscode Chat Proxy

ytechai
Free

Lets VS Code Chat use Kimi, MiMo, DeepSeek and Qianfan models by translating three API protocols.

1.3k installs/moMIT

Similar apps

All apps
OSappInfrastructure
Clean scanStatic scanned
Serves a local web dashboard that refreshes every 30 seconds and keeps its figures in a SQLite database. Only new or changed log entries are processed, and results can be broken down by model or by folder.

Omp Stats

oh-my-pi
Free

Reads your local AI session logs and charts requests, errors, tokens per second and cache rate.

352.5k installs/moMIT
OMappInfrastructure
Clean scanPublisher verified
Heavy chat requests queue instead of failing, a shared quota is split fairly across pooled keys, and long context can be compressed. Cost and usage headers come back from every endpoint, with per-key dollar spend quotas.

Omniroute

diegosouza.pw
Free

Routes your AI requests across many providers through one OpenAI-compatible API.

316.3k installs/moMIT
ACappInfrastructure
Clean scanStatic scanned
Works with OpenAI, Anthropic, Gemini, Mistral, DeepSeek, OpenRouter and OpenAI-compatible services such as Ollama, using your own API keys. It can also sum up the whole run.

AI Ctrf

ctrf-io
Free

Adds an AI explanation of each failed test to your CTRF test report, using the model provider you pick.

48.5k 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.