Verifica el trabajo de los asistentes de codificación con IA ejecutando cambios en workers aislados y realizando reejecuciones de pruebas independientes y escaneos de secretos.
También conocido como rayson-tech/nomarmy
- Stars
- 4
- Herramientas
- —
- Descargas, 30 días
- —
- Última versión
- 0.1.0-beta.19
- Último commit
- 9 nov 2026
- Licencia
- Apache-2.0
¿Qué es nomArmy MCP?
nomArmy es un MCP server. Verifica el trabajo de los asistentes de codificación con IA ejecutando cambios en workers aislados y realizando reejecuciones de pruebas independientes y escaneos de secretos.
Resumen generado a partir del README del proyecto
Acerca del MCP server de nomArmy
nomArmy proporciona una capa de verificación para asistentes de codificación con IA como Claude Code, Codex o Cursor. En lugar de confiar en la afirmación de un agente de que una tarea está completada, este sistema utiliza workers aislados llamados noms para ejecutar cambios dentro de un contenedor Podman. Estos workers operan en un entorno restringido sin acceso a la red y sin credenciales del host para garantizar la seguridad durante el proceso de construcción.
Después de que un nom completa su tarea, el sistema valida el trabajo de forma independiente leyendo el git diff real, ejecutando pruebas en un sandbox nuevo y realizando una comprobación de reversión para asegurar que las pruebas realmente detecten los cambios previstos. También incluye escaneo de secretos para evitar filtraciones accidentales. Los usuarios pueden configurar varios agentes usando API keys, suscripciones o modelos locales a través de llama.cpp. La configuración requiere Git, Node y Podman, con requisitos de memoria específicos para usuarios de macOS.
Qué puedes hacer con él
- 1Verificar cambios de código generados por IAUn asistente de IA puede delegar una tarea de programación a un worker aislado para demostrar que los cambios realmente pasan las pruebas existentes.
- 2Automatizar el desarrollo de funcionalidades de extremo a extremoUn desarrollador puede activar un flujo de trabajo completo que va desde la planificación inicial hasta la construcción, revisión y aceptación final.
- 3Prevenir filtraciones de secretos en los commitsEl sistema escanea automáticamente el código en busca de información sensible antes de que cualquier cambio se realice en una rama.
- 4Realizar validación de pruebas independienteLa herramienta asegura que las pruebas sean significativas revirtiendo los cambios y comprobando si las pruebas siguen pasando sin el código nuevo.
Escrito a partir del README del proyecto. Cada caso de uso se verifica con una cita del mismo.
Cómo instalar nomArmy MCP
Formatos verificados el 10 nov 2026Añadir a CursorAñadir a GooseInstalar nomArmy MCP en Claude Code
$ claude mcp add nomarmy -- npx -y nomarmyInstalar nomArmy MCP en Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"nomarmy": {
"command": "npx",
"args": [
"-y",
"nomarmy"
]
}
}
}Instalar nomArmy MCP en VS Code
.vscode/mcp.json
{
"servers": {
"nomarmy": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"nomarmy"
]
}
}
}Instalar nomArmy MCP en VS Code CLI
$ code --add-mcp '{"name":"nomarmy","type":"stdio","command":"npx","args":["-y","nomarmy"]}'Instalar nomArmy MCP en Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"nomarmy": {
"command": "npx",
"args": [
"-y",
"nomarmy"
]
}
}
}Instalar nomArmy MCP en Codex
$ codex mcp add nomarmy -- npx -y nomarmyInstalar nomArmy MCP en Codex config.toml
~/.codex/config.toml
[mcp_servers.nomarmy] command = "npx" args = ["-y", "nomarmy"]
Instalar nomArmy MCP en Gemini CLI
$ gemini mcp add -s user nomarmy npx -- -y nomarmyInstalar nomArmy MCP en Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"nomarmy": {
"command": "npx",
"args": [
"-y",
"nomarmy"
]
}
}
}Verificaciones automáticas
Ejecutado 14 nov 2026Informe completo →Pasó nuestras verificaciones automáticas. Esto no es una auditoría de seguridad: lee el código y dale al servidor el acceso más limitado que necesite. Cómo funcionan las verificaciones
- Repositorio de origen vinculado y accesiblerayson-tech/nomarmy is public and reachablegithub.com/rayson-tech/nomarmy ↗Aprobado
- El paquete indica este repositorio como su origennomarmy names rayson-tech/nomarmy as sourcenpmjs.com/package/nomarmy ↗Aprobado
- Procedencia de la compilación (atestación de Sigstore)No build attestation published for this releaseNo verificado
- Licencia de código abierto (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Aprobado
- Commit o lanzamiento en el último añoLast commit or release 2026-11-09github.com/rayson-tech/nomarmy ↗Aprobado
- OpenSSF ScorecardNo verificado
- El nombre del paquete no es similar a un paquete popularNo popular package one edit away from nomarmyAprobado
- No hay avisos críticos en el paquete ni en sus dependencias150 resolved dependencies checked; no critical advisoryosv.dev ↗Aprobado
- Sin instrucciones ocultas para el modelo0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersAprobado
- Las herramientas destructivas están etiquetadasNo verificado
- El endpoint remoto responde al handshake de MCPNo verificado
README
Ver en GitHubYour coding assistant plans; sandboxed workers build; nothing counts until nomArmy has checked it.
AI coding workers are confident. Their "done, all tests pass" is a claim, not evidence. nomArmy lets your coding assistant (Claude Code, Codex or Cursor) hand work to workers called noms, then checks every change itself before anything is committed: the real diff, your tests run in a fresh sandbox, a check that those tests actually catch the change, and a secret scan.
TL;DR
- Have Git, Node 24.16+ (or 26.1+), Podman, and Claude Code, Codex or Cursor installed and signed in. On macOS, give Podman 8 GiB:
brew install podman && podman machine init --memory 8192 && podman machine start. Windows is supported with the engine in WSL2. Follow the Windows setup. - Install and set up:
npm install -g nomarmy cd your-project nomarmy setupnomarmy setupis a playbook. It shows a checklist and runs the next step each time you say yes:
Stop anytime;✓ Where models run: hosted ✓ Installed: OpenClaw 2026.10.3 → Agents: add a hosted agent Roles: add an agent first This repo: configure this project Check: verify the installation Run `nomarmy agents add` now? [Y/n]nomarmy setuppicks up where you left off. Want every step spelled out? Example setup: Claude Code, Codex and an API key goes command by command. - Use it: restart Claude Code in the project and ask it to use nomArmy for one small bug that has a test. When that works, try
/feature <what you want built>.
Prefer a plugin? After step 2, Claude Code users can run /plugin marketplace add rayson-tech/nomarmy and /plugin install nomarmy@nomarmy instead of using nomarmy connect; Codex works too (plugins).
Stuck? nomarmy doctor checks the machine and nomarmy health checks everything nomArmy runs on. Upgrading later? nomarmy update.
How every byte gets verified
- Your coding assistant, the General, briefs a job: a task, acceptance criteria, and the tests that prove it.
- nomArmy creates a git worktree from your branch and runs the nom in a Podman sandbox with no network and no host credentials. (One exception, the Claude subscription: see Security posture.)
- The nom edits, runs tests, and ends with a four-line report:
STATUS,TESTS,NOT_DONE,NOTE. - nomArmy treats that report as a claim and checks the evidence itself:
- reads the real diff from git, not the nom's description of it
- runs your verification profile in a fresh sandbox
- reverts the production change and reruns the tests: a test that still passes proves nothing, so the job goes to review instead of being committed
- blocks on secrets, and flags tests made to pass (new skips, stubbed imports) and code nothing calls
- Only then does it commit, on the nom's own branch. It never merges into yours: reviewing and integrating stay with the General, and with you.
Failing verification stays failed, unconditionally. A malformed report isn't automatically a failure: if the repository changed, nomArmy verifies independently and may recover the work. And the checks aren't the General's to waive: a repo's .nomarmy.yml policy (on by default for new repos) makes verification and the revert check mandatory for every job.
Showing what was checked. When a /feature run finishes, the General gets a "Verified by nomArmy" block for the pull request: how many "done, tests pass" claims held up, how many nomArmy caught and why, and the new tests shown to fail without their change. nomarmy stats --share prints the same for any period, and nomarmy stats --badge writes a README badge like nomArmy | 78 claims checked · 11 caught. Every number comes from the verified records.
Checking without building costs nothing: mode: verify runs a verification profile against any branch, with no worker and no model tokens.
Want deeper checks? Three optional validators go further, each only adding review flags: mutation testing (do the tests pin down the changed lines?), Jev (do a scout's citations support its findings, does a report match its diff?, on TypeSafe or a compatible server on your own machine) and a model judge (acceptance criteria, weakened tests).
Where the work runs
- Agents say where a job can run: an API key, your own Claude, ChatGPT, Muse Code or Grok subscription (or another OpenClaw provider), or a local model on llama.cpp.
- The army says which role runs on which agent: Sr and Jr devs build, a security analyst and a data architect review, a PM checks the plan, a PO accepts.
/featureruns a whole feature end to end, from plan through build, review and acceptance, and hands you a branch to merge.- Harnesses give each repo the right sandbox: Go, Rust, Python and Node (mixed repos too), Playwright browser tests, and fake services like a mock login server, all offline. Adding one never touches core code.
What you get is work you don't have to take on faith, not cheaper work. Delegating costs the General tokens too, for briefing and review: on small, already-diagnosed tickets we measured 4 to 8 times more of the General's tokens than fixing the bug directly, with break-even around 150 lines of context a fix needs to read (the measurements). It pays off on bigger tickets, parallel work, and anywhere you'd otherwise trust an agent's say-so.
Have a GPU or a Mac with plenty of memory? Choose "a local model" in nomarmy setup: no per-token bill and your code stays home, but you pay in hardware, power and speed. nomarmy sizing tells you what fits. A shared model server works too.
Developed and maintained by Rayson Technologies. This is a beta (0.1.0-beta): settings carry across upgrades (see config compatibility).
Docs
| Install | Every setup: hosted (API keys and subscriptions), a local model on macOS, Linux, Windows with the engine in WSL2 or DGX Spark, a shared model server, Bedrock |
| Example setup | Claude Code, Codex and an API key, command by command |
| Agents and the army | Where a job can run, who does what, usage limits, picking an agent |
/feature runs |
A feature end to end, and watching what nomArmy is doing |
| Your repository | .nomarmy.yml, verification, dependencies, private registries, what nomArmy checks |
| Validators | Optional deeper checks: mutation testing, Jev, a model judge |
| Harnesses | Ecosystem registry, detection, network levels, and requirements |
| Configuration | Settings, swapping the local model, sizing, admission |
| Reference | Every CLI command and MCP tool |
| Security posture | What the sandbox holds back, and the one exception |
| FAQ | Which model for which role, switching models, usage limits |
| Troubleshooting | Symptoms and fixes |
Security
A nom gets a writable git worktree inside a Podman sandbox and nothing else: no network, no host credentials, no Podman socket. Every model call is made by OpenClaw on your machine, never from inside the sandbox. Verification can climb a network ladder one rung at a time (fake services on a private network, then an allowlist you approve for a test tenant), but noms never leave network none. The exception is a Claude subscription, whose tools run on your machine, so nomArmy refuses build jobs on it unless you allow it. Never hand a nom production credentials, deployment access or SSH keys. Details: Security posture; to report a vulnerability, SECURITY.md.
Status
| Capability | Status |
|---|---|
| Verification core: worktrees, nomArmy-owned git, independent verification, the revert check, kept failed worktrees | Working, end-to-end tested |
mode: verify, secret scanning (secretlint, hard block), test-workaround and unwired-code checks |
Unit and live tested; the heuristics are review flags |
Scout and decompose modes, auto_union |
Unit and live tested |
| Agents: API keys | Live-verified with xAI; other providers built to OpenClaw's documented interface |
| Agents: subscriptions | ChatGPT (Codex) sandboxed and live-verified; Claude and Muse Code live-verified, but their tools run on the host (scout and review by default) |
| Local (llama.cpp) and Bedrock profiles | Working |
The army and /feature |
Used daily on nomArmy itself and our own products: 783 jobs from September 18 to October 10, 2026 (measured results) |
| Harnesses: Go, Rust, Python, Node and mixed repos; Playwright; fake services | Live-verified offline |
| Private registries and a verification-only network allowlist | Live-verified; each passed an independent security review |
| Validators: mutation testing, Jev, a model judge | Unit and live tested; Jev and the judge evaluated on real job records |
nomarmy stats |
Checked against a hand-built report on real job records |
What we've learned from real runs, including where delegating pays and where it doesn't, is in docs/findings.md.
Known limitations
- A Claude subscription isn't sandboxed. Its tools run on your machine, so implement jobs on it are refused unless you set
allow_host_tools: true. See Security posture. - Your own compose services aren't started yet. A verification profile that needs a real database from your compose file (
environment: basicor higher) reportsnot_runrather than running without it (and the compose parser doesn't resolve YAML anchors). Fake services from harnesses, like the mock login server, do run. - Private registries don't cover Poetry or Yarn Berry yet: Poetry can't guarantee a credentialed install runs no package code, and Yarn Berry doesn't read
.npmrc. uv, pip wheels, npm, pnpm, Yarn Classic and bun work. See Private registries. - A model a vendor lists but refuses is caught at dispatch, with a test call. The first job on a model that has never worked for its agent waits a few seconds for a one-token test call; a refusal (gpt-6-sol on a ChatGPT plan) is reported and remembered instead of costing the job. An inconclusive test call (a timeout) lets the job through.
- Claude subscription token counts come from the Claude CLI's own session log, since OpenClaw sees only the final reply; totals include cache reads and writes.
- Test-workaround detection is a flag, not a verdict: a legitimate new skip still gets flagged.
- Deploy-time failures need your own check. See Add a check for what unit tests can't see.
- Same-host sandboxes: the MCP server, OpenClaw and every job's sandbox run on the machine with the coordinator. Only the model can be elsewhere.
More
- docs/findings.md: what real runs taught us.
- docs/experiments: the measured write-ups behind them.
- policies: how scouts and reviewers are held to account.
- CONTRIBUTING.md, SECURITY.md, CODE_OF_CONDUCT.md.
Configuration variables are NOMARMY_*; a legacy RAYSON_* variable is translated once at load, with a deprecation warning.
Licensed under Apache 2.0.
Preguntas sobre nomArmy MCP
¿Cómo agrego nomArmy MCP a Claude Code?
Ejecuta claude mcp add nomarmy -- npx -y nomarmy en tu terminal. Añade --scope user para que esté disponible en todos los proyectos.
¿Cómo agrego nomArmy MCP a Cursor?
Abre ~/.cursor/mcp.json y añade el servidor en mcpServers, usando la configuración de Cursor que se muestra en la sección de instalación de arriba.
¿Cómo verifica nomArmy los cambios de código?
Crea un git worktree, ejecuta el código en un sandbox de Podman sin acceso a la red y realiza una comprobación de reversión (revert check) donde las pruebas deben fallar si se deshace el cambio.
¿Es segura la ejecución del código?
Sí, los workers se ejecutan en un sandbox de Podman sin acceso a la red y sin credenciales del host.
¿Puedo ejecutar modelos localmente?
Sí, puedes optar por ejecutar un modelo local a través de llama.cpp para mantener tu código en tu propia máquina.