Skip to main content
Glama
deenesjakoruzh
no-human-ai

no_human

by no-human-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

no_human

De ticket a pull request revisado.Gratis y de código abierto, en tu máquina.

latest release CI python 3.12+ license MIT

getnohuman.com · Inicio rápido · Documentación · Míralo trabajar en un sprint

Download for macOS Download for Windows Download for Linux

▶ Mira el bucle — un ticket entra, un pull request revisado sale; todo el bucle en 57 segundos.

La fábrica de código con IA en la que puedes confiar:

  • Un plan antes de cualquier código, a partir del ticket y de lo que encuentre en tu repositorio.

  • Una revisión adversarial. Un modelo diferente, contexto nuevo, herramientas de solo lectura, con la instrucción de refutar "hecho". Obtienes una lista de verificación de aprobado/reprobado que cita archivo y línea — nunca una autoevaluación numérica.

  • Una protección contra manipulación. Pruebas eliminadas, nuevos "skips", una aserción convertida en tautología — bloqueado antes de que se gaste un token de revisor.

  • Prueba de que la corrección arregló el error. Para una corrección de errores, las pruebas ofrecidas como evidencia deben fallar en la base de fusión y pasar en el nuevo árbol — la puerta de reproducción lo exige, y puedes requerirlo para cada cambio.

  • Tus pruebas se ejecutan, localmente y opcionalmente a través de tu CI.

  • Una parada honesta. Cuando no puede terminar, se detiene con una pregunta específica en lugar de inventar un diff plausible.

Instalación

Sea cual sea la forma de instalación, necesitas una credencial de Claude: un token OAuth de claude setup-token (suscripción personal o empresarial), así que instala primero la CLI de Claude Code — npm install -g @anthropic-ai/claude-code, o curl -fsSL https://claude.ai/install.sh | bash. La aplicación de escritorio también llama a esa CLI para cada tarea. Para pagar a Anthropic directamente, establece llm.auth_mode: "api_key" y pon tu ANTHROPIC_API_KEY en ~/.no_human/.env.

Una línea (CLI + tablero)

uv tool install no-human   # or: pipx install no-human — the wheel ships the board
nh init && nh doctor       # token, config, first repo; then prove the install is real

Aplicación de escritorio

Download for macOS Download for Windows Download for Linux

Cada versión incluye un SHA-256 junto al artefacto. Notas de plataforma y el recorrido de primera ejecución: docs/quickstart.md.

Desde el código fuente

git clone https://github.com/no-human-ai/no_human.git && cd no_human
uv sync                 # installs the `nh` entry point into .venv
(cd web && npm install && npm run build)   # builds the board (cold first install can take minutes)
uv run nh init          # token, config, first repo (about 2 minutes)
uv run nh doctor        # verify the install is real before relying on it

La compilación web no es opcional si quieres el tablero: un checkout del código fuente no incluye web/dist, así que sin ella nh start sirve solo la API y no renderiza ninguna interfaz. Necesita Python 3.12+, uv, git y Node con npm para la compilación del tablero.

Related MCP server: letmediff

Ejecutar una tarea

Ejecuta nh sin argumentos para el shell: tus carriles, un seguimiento de eventos en vivo y una entrada donde describes una tarea en inglés sencillo. Todos los comandos siguientes siguen funcionando.

nh                                   # the shell
nh start                             # board + worker on 127.0.0.1:8420
nh task add https://github.com/org/repo/issues/42 --repo ~/git/repo
nh status                            # needs-you / working / waiting / done
nh review <id>                       # the reviewer's evidence checklist
nh diff <id>                         # the diff it wants to ship
nh approve <id>                      # your approval squash-lands the PR (git.approve_identity)
nh reject <id> --reason "..."        # send it back with feedback

Integraciones

Apunta no_human al rastreador que ya usas y trae los tickets a tu tablero — el filtro de un rastreador vive en tu configuración, nunca en el texto de la propia tarea, y un error de transporte se registra y reintenta en el siguiente tick en lugar de bloquear el grupo.

Rastreador

Cómo llegan los tickets

Filtro que configuras

Jira Cloud

Consultados vía REST search/jql (HTTP Basic email:token)

integrations.jira.jql

Linear

Consultados vía la API GraphQL

integrations.linear.team_key + state_types + label

monday.com

Consultados vía GraphQL v2

integrations.monday.board_id + status_column + todo_labels

Con la escritura inversa activada (write_back, desactivada por defecto), el ticket se mueve con la tarea — emparejado por categoría de estado, tipo o la etiqueta que nombres, nunca un id de transición codificado — y recibe el enlace del PR; una tarea que necesita un humano se comenta, nunca se transiciona. Los issues de GitHub y GitLab se importan como tareas por URL, y los PRs o MRs se abren en tu propio host; Slack y Teams reciben un mensaje cuando una tarea te necesita; Jenkins y CircleCI pueden ejecutar tus capas de prueba y controlar el bucle. Configuración para cada uno: docs/adapters.md.

Mira el flujo de Jira de principio a fin — tickets sincronizados desde un tablero de Jira, definidos, implementados y entregados como un pull request que pasó la revisión (haz clic para el video completo con cada paso):

Jira flow demo

Servidor MCP — entrégale trabajo desde el agente en el que ya estás

no_human incluye un servidor MCP (Model Context Protocol): un puente stdio, construido sobre el SDK oficial de Python MCP, que permite a Claude Code, Cursor o cualquier cliente MCP presentar trabajo a tu no_human local y verificar su estado.

nh mcp-serve        # the MCP server, over stdio

Dos herramientas, y no más:

Herramienta

Qué hace

task_add(title, description, repo_path)

Registra una tarea. no_human luego la planifica, escribe el cambio, ejecuta tus pruebas, hace que un segundo modelo la revise y abre el pull request.

task_status(task_id_or_external_id)

Devuelve el estado actual de esa tarea — estado, intentos, el enlace del PR una vez que exista.

Habla con tu propio no_human en http://127.0.0.1:8420 y con nada más: sin autenticación, porque esa dirección es localhost, y sin ningún servicio nuestro en el medio. Para Claude Code, el mismo servidor se incluye como plugin — apúntalo a plugins/no-human/ y las dos herramientas aparecen en tu sesión.

// .mcp.json
{ "mcpServers": { "no_human": { "command": "nh", "args": ["mcp-serve"] } } }

Documentación

quickstart.md

De cero a la primera tarea, por plataforma

configuration.md

Cada ajuste y valor predeterminado

verification.md

Las puertas, el bucle acotado, los límites

security.md

Límite de autenticación, la regla de nunca fusionar, protecciones

blockers.md

Escalamiento, vigilante de activación, nh reply

adapters.md

Entrada, contexto, backends de VCS y CI

eval.md

Conjunto dorado, puntuación de reproducción, modo sombra

CHANGELOG.md

Qué cambió, por versión

Desarrollo

uv sync
uv run pytest -q
uv run nh --help

Los issues y pull requests son bienvenidos; ejecuta uv run pytest -q antes de enviar.

Si no_human te ahorró un ciclo de revisión, una estrella ayuda a otras personas a encontrarlo: GitHub stars

Licencia

MIT — consulta LICENSE. La licencia cubre el código, no el nombre: TRADEMARK.md es la política sobre el uso de "no_human" y el logotipo. Empaquetar un binario conlleva obligaciones que el árbol de código fuente no tiene, enumeradas en THIRD-PARTY-NOTICES.md.

Available Tools

2 tools
task_addA

Create a no_human task via POST /api/tasks (source="mcp"). Returns compact JSON {"task_id": str, "source": str} — source is whatever the server actually stored (the "mcp" source is first-class, see module docstring).

ParametersJSON Schema
NameRequiredDescriptionDefault
titleYes
repo_pathYes
descriptionYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A3.9/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must disclose behavioral traits. It does so by specifying the return format (compact JSON) and noting that the source is whatever the server actually stored, which informs the agent of potential variability. It also mentions the source is first-class, referencing module docstring, which adds context. However, it does not discuss side effects, error states, or idempotency, but given it's a creation endpoint, the info is reasonably transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, two sentences, and front-loaded with the core purpose. Every sentence adds value: the first states the action and endpoint, the second clarifies the response format and a behavioral nuance. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool is simple (3 required params, no nested objects), and there is an output schema (though not provided in the input), the description is fairly complete. It covers the endpoint, source handling, and return format. It could mention potential errors or idempotency, but for a POST creation endpoint, it covers the essentials. The absent annotation makes it carry more weight, but it handles that well.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 0% description coverage, so the description must compensate. It explains that the 'source' parameter (implied by the endpoint) is set to 'mcp' and describes the response, but it does not provide specific details on 'title', 'description', or 'repo_path' beyond what's in the schema. However, it adds value by clarifying the 'source' semantics and response structure, which is useful for the agent. Since all parameters are required and self-explanatory from their names, the description's addition is reasonably helpful.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: creating a no_human task via a specific endpoint and source. It clearly distinguishes from the sibling tool 'task_status' which presumably handles status queries, by focusing on task creation. It uses a specific verb ('Create') and specifies the resource ('task'), making it clear.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use this tool (to create a no_human task) but does not explicitly contrast with alternatives. Since there is only one sibling and no elaboration on when not to use it, it only provides moderate guidance. It does not mention any prerequisites or conditions for use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

task_statusA

Fetch a task's full current state via GET /api/tasks. Resolves by task id (or unique id prefix) first; if that 404s, falls back to matching external_id across the task list (GET /api/tasks does not index by external_id, so this is a client-side scan). Returns the complete task object as compact JSON.

ParametersJSON Schema
NameRequiredDescriptionDefault
task_id_or_external_idYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.8/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description fully carries the burden and discloses important non-obvious behavior: resolution by task id or unique prefix, fallback to a client-side external_id scan, and the reason for that fallback. This gives the agent accurate expectations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences with no filler. Each sentence adds functional value: the endpoint, the lookup strategy, and the return format.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the single parameter, presence of an output schema, and absence of annotations, the description is sufficiently complete. It covers the lookup method, fallback behavior, and return representation without needing to describe output schema fields.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema provides only the parameter name and type with no description, and schema description coverage is 0%. The description compensates fully by explaining that the parameter accepts a task id, unique id prefix, or external_id and by detailing the resolution order.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool fetches a task's full current state via a specific endpoint. It uses a precise verb and resource, and the read-oriented purpose distinguishes it from the sibling task_add.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides clear context for when to use the tool: whenever a task's current state is needed. It does not explicitly name alternatives or exclusions, but the intended use is evident.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 2 tool updatesv0.1.0
    • First observedtask_add
    • First observedtask_status
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.1/5.0

Scored across 2 tools

Disambiguation5/5

task_add creates a task while task_status retrieves the current state of a task; their purposes are entirely distinct with no overlap. An agent would not confuse which tool to call.

Naming Consistency4/5

Both tools share a consistent task_ prefix and use snake_case, so they form an obvious family. The minor deviation is that one second token is a verb (add) while the other is a noun (status), but at only two tools this is easy to parse.

Tool Count3/5

Two tools is on the thin side for a task-management server, though the narrow create-and-check scope keeps it acceptable. It falls in the borderline range rather than feeling egregiously over- or under-built.

Completeness3/5

The domain appears to be task management, and the server supports creation plus status lookup, which covers the core add-and-monitor workflow. Missing operations include list, update, cancel/delete, and resubmission, which are notable but work-around-able for a minimal no_human API.

Maintenance

ActivityActive
ResponsivenessResponsive

Resources

Related MCP Connectors

Related MCP Servers