open-mercato/open-mercato

The AI-Engineering Foundation Framework for business apps: open-source TypeScript, with multi-tenancy, RBAC, events and domain modules already decided as conventions and specs, so Cursor, Claude Code and Codex build features instead of re-deciding architecture. Start with 80% done.

Open Mercato is an open-source framework for building business back-offices (CRM, inventory, sales, etc.) with the help of AI coding agents like Claude Code, Codex, or Cursor. The main idea: instead of asking an agent to create an app from scratch (which often leads to messy, inconsistent code), you start with a pre-built foundation that already has dozens of working modules, clear architecture rules, and a set of agent-friendly tools. You get an 80% complete system out of the box and use AI to build the missing 20% — the part unique to your business.

How it works:

  • Scaffold a new project with npx create-mercato-app – picks a template (classic, CRM, warehouse, empty) and your preferred AI agent.
  • The generated app includes an AGENTS.md plus a collection of “skills” that tell the AI agent exactly where new code should go: which folder, how to structure a module, how to run tests, etc.
  • You work in stages: get a running back office in about 10 minutes, then write a spec for your custom feature (e.g., “roast batches” for a coffee roaster), approve it, and let the agent implement it phase by phase.
  • For unattended work, Cezar (also open-source) runs agent tasks on a schedule or when GitHub events happen (e.g., a PR is opened), without ever merging code by itself.

The framework is written in TypeScript on Next.js and PostgreSQL, and is MIT-licensed for the core. The README stresses that it’s built for teams and developers who already use AI assistants but found they need more structure and consistency across larger codebases.

Related

  • Project
    AgentDock/AgentDock

    A TypeScript framework for building AI agents with configurable determinism, allowing developers to balance LLM creativity with predictable, structured workflows.

  • Project
    google/adk-docs

    A code-first, model-agnostic toolkit for building, evaluating, and deploying sophisticated AI agents and multi-agent systems.

  • Project
    agent0ai/dox

    A lightweight framework using a hierarchy of AGENTS.md files to give AI agents precise project context and prevent blind edits during coding.

  • Project
    MaxGfeller/open-harness

    A framework based on Vercel's AI SDK for building general-purpose AI agents with built-in support for tool use, session management, and composable middleware.

  • Project
    AgnesAI-Labs/agnes-harness

    Agnes Harness is a developer-focused framework for building and deploying AI agents that integrate with enterprise business systems and physical hardware, emphasizing auditability, human-in-the-loop approvals, and reusable plugin architectures.