Ross ROSS = Recommend OSS · open-source software intelligence for agents

wrtnlabs/autobe

AI Vibe Coding Agent of TS backend server, enhanced by compiler skills, generating 100% working code observed · 2026-08-28

github.com/wrtnlabs/autobe · homepage · TypeScript · AGPL-3.0 (copyleft) observed · 2026-08-28

Health v2 · maintenance only

70/100

  • Activity 89
  • Release rhythm 66
  • Longevity 35
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 0.0
  • age_days: 492
  • days_rel: 145
  • days_push: 70
  • n_releases_24m: 87

Full methodology

Adoption not part of the score

1359 stars · 156 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

AutoBE is an AI-powered backend builder that turns natural language requirements into complete NestJS/TypeScript backend applications with Prisma schemas, OpenAPI specs, and e2e tests. It uses a waterfall-style pipeline with specialized AI agents and compiler validation (Prisma, OpenAPI, TypeScript) to guarantee 100% compilable generated code.

Use cases

  • generate a backend server from a natural language description
  • build a NestJS API without writing code
  • create a Prisma database schema from requirements
  • prototype a full-stack backend with e2e tests automatically
  • generate a type-safe SDK client for my API
  • vibe-code a complete backend application
  • no-code backend generation for non-programmers

When to choose

  • you want a working TypeScript/NestJS backend quickly from plain-language requirements
  • you need guaranteed-compiling generated code with e2e tests and documentation
  • you're prototyping MVPs, CRUD apps, or standard web service backends
  • you want a learning reference for backend architecture patterns

When to avoid

  • you need a stack other than TypeScript, NestJS, and Prisma
  • your project requires highly custom, non-standard architecture the agent can't express
  • you need fine-grained manual control over every implementation detail from the start
  • your license requires permissive terms (AutoBE is AGPL-3.0)

Facets

framework · maturity active

agent-framework llm-inference web-framework orm e2e-testing api-framework artificial-intelligence backend web-development developer-tools self-hosted vibe-coding ai-coding-agent no-code nestjs prisma openapi compiler-driven code-generation waterfall-model function-calling ai-agents automation nodejs typescript web-server

10 sources

Member repositories

RepositoryRoleHealth v2
wrtnlabs/autobemain70

For agents

markdown · JSON · MCP: product_card(name="wrtnlabs/autobe")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem