Skip to content
bmad-architecture

Self-hosted alternatives to bmad-architecture

5 self-hosted AI Skills apps to use instead, best rated first.

Top picks

  1. C

    claude-to-deerflow

    Launch

    claude-to-deerflow is an agent skill that lets an assistant send messages and questions to a running DeerFlow instance through its HTTP API. DeerFlow is an AI agent platform built on LangGraph that orchestrates sub-agents for research, code

    Self-hosted

  2. O

    open-notebook

    Launch

    open-notebook is an agent skill for organising research with Open Notebook, a self-hosted alternative to NotebookLM. It arranges sources, notes and AI conversations into research notebooks. Sources can be PDFs, web pages, audio, video and O

    Self-hosted

  3. R

    Reactive Resume

    Launch

    Reactive Resume is a free and open-source resume builder for writing resumes and cover letters, checking the work, and tracking job applications. You create a free account, import an existing resume or start from scratch, and see the finish

    Open sourceSelf-hosted

  4. S

    self-hosted-funnel-launch

    Launch

    Self-hosted funnel launch is an agent skill that takes a funnel from an empty install to published on infrastructure you control, using the Autonnel funnel builder, which is licensed Apache-2.0. The result covers a landing page, checkout, a

    Self-hosted

  5. G

    get-convex/convex-backend

    Launch

    Convex is an open-source reactive database for web app developers. It combines a database, a place to write server functions in pure TypeScript, and client libraries that keep the app's data live, so screens update as the data changes. Beca

    Self-hosted

About bmad-architecture

B

bmad-architecture

Work out and record the architecture decisions

bmad-architecture is a skill from the BMad Method project for working out and recording the architecture decisions that keep separately built parts of a system consistent. It produces a short architecture spine, a consistency contract that fixes only the invariants that stop independently built units from diverging, such as the design paradigm, the boundary and dependency rules, how state is changed, and who owns shared data. Everything structural, such as the stack, the file tree and the full data shape, is treated as a seed at the start and is owned by the code once it exists. The skill applies a test to decide what belongs: if two units one level down could be built independently and choose incompatible approaches, the decision is fixed here, but only when the call is non-obvious and a real trade-off. Other points go under a deferred list. It works in two paths. The coaching path, which is the default, works through open questions together and pushes back where a decision is thin, and the fast path drafts the whole spine quickly with assumptions tagged for correction. The load-bearing calls, such as the paradigm, the stack and the major boundaries, are presented with realistic alternatives rather than silently made. It suits teams building a system from several parts who need the parts to fit together. Because the spine governs future work, review it with the people who will build each part, and revisit it when the system changes. The skill passes Gen Agent Trust Hub on skills.sh, and Socket and Snyk were not shown in the scanned listing. It has about 9,600 installs. Install it with npx skills add https://github.com/bmad-code-org/bmad-method --skill bmad-architecture.

Price
Free
Made by
bmad-code-org
Category
AI Skills
Website
github.com/bmad-code-org/bmad-method/bmad-architecture