3 findingsStatic scanned
Runs OpenAI's Codex coding agent locally on your computer from the command line.
71.3M installs/moApache-2.0
Mvpscale Mm3
mvpscale · Agent
MM3 is a memory and decision layer for coding agents, currently in beta. Your agent sends a batch of yes or no checks about a piece of code, each asked three ways, and gets scored answers and a consensus back. Every request, verdict and the problem being worked on goes into an append-only ledger, so repeated questions on unchanged code are answered without a call. New questions go to a TypeSafe-compatible classifier endpoint with your own key and base URL; without a key a built-in sample provider gives canned, labelled answers.
Written by ooruby from the README of @mvpscale/mm3 0.1.5.
Not claimed by its maker. Is this yours? Prove it and answer the findings
Why it's useful
Gives each check an agent runs a consistent form, a score and a record, so what you learn about your codebase is kept and reused.
What you could do with it
- Have your agent ask several yes or no questions about one part of your code in a single call.
- Add a dry run to a request to validate it and count its questions without making a call.
- Read the report of where your agents keep going wrong, built from past runs in the ledger.
Written from its documentation: what it says it can do, not what our checks found.
Maintenance
Not measuredNo 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
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
MM3, make and model for coding agents: MAK³ uses what is proven, MDL³ learns what is missing, with compact yes/no checklists, a calibrated consensus, and a log that learns where agents go wrong.
Compare with
Compare all 4How 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 0.1.5, the file with digest sha512-uTYDxANFURTz8gZKtsJ6PS3aPvRRqDCOYxAk3ZlQ9XsS5ObyCz3s05uivzo6gMVKQWLgiu8PWZ5IJgKzzuTkIw==, 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.
Adding it
Run it with:
npx -y @mvpscale/mm3@0.1.5Pinned to 0.1.5, 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
- @mvpscale/mm3
- Version read
- 0.1.5
- Resolved
- 2026-10-10
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/mvp-scale/mm3
- Commit
- 035c10697964
- 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.
[](https://ooruby.com/market/mvpscale-mm3)About this listing
- Kind
- Agent
- Category
- Developer tools
- Pricing
- Free
- Sandbox
- No
- Hosted
- No
- Updated
- 2026-10-09
Similar agents
All agentsVerification 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.