InsForge/InsForge

The all-in-one, open-source backend platform for agentic coding. InsForge gives your coding agent database, auth, storage, compute, hosting, and AI gateway to ship full-stack apps end-to-end.

What it solves

InsForge is an open-source backend platform designed specifically for agentic coding. It provides coding agents with the necessary infrastructure—database, authentication, storage, and compute—to build and deploy full-stack applications end-to-end without requiring a human backend engineer.

How it works

Coding agents interact with the platform through two primary interfaces:

  • MCP Server: A self-hosted or cloud-based server that exposes InsForge's operations as tools for any Model Context Protocol (MCP) compatible agent.
  • CLI + Skills: A cloud-only interface where agents invoke specific skills directly from the terminal.

These interfaces allow agents to read backend context (such as schemas and logs) and configure backend primitives (like deploying edge functions or running database migrations) just as a human engineer would.

Who it’s for

Developers building AI coding agents that need a target backend environment where the agent can autonomously manage infrastructure and ship full-stack apps.

Highlights

  • All-in-one Backend: Includes Postgres database, S3-compatible storage, and user authentication.
  • AI Gateway: An OpenAI-compatible API that provides access to multiple LLM providers.
  • Edge Functions: Serverless code execution on the edge.
  • S3 Compatibility: Supports local filesystem storage or external S3-compatible stores (AWS S3, MinIO, etc.).
  • Flexible Deployment: Can be self-hosted via Docker Compose or deployed via one-click platforms like Railway or Zeabur.

Related

  • Dispatch
    InsForge: An Open-Source Backend Platform for AI Coding Agents

    InsForge provides a CLI-driven infrastructure platform that allows AI coding agents to deploy, operate, and debug backends independently, featuring backend branching and dedicated debug agents.

  • Project
    caipe-io/ai-platform-engineering

    An open-source platform for building, deploying, and governing AI agents and agentic workflows, specifically designed for platform engineering and enterprise operations.

  • Project
    truefoundry/trueforge

    TrueForge is an open‑source Node.js harness that runs LLM agents, handling model calls, tool integration, sandboxed execution, session storage, approvals, and UI. It works with any OpenAI‑compatible model, offers a chat UI, HTTP API, and TypeScript SDK, and can run locally (SQLite) or in hosted mode (Postgres + Redis).

  • Project
    IBM/mcp-context-forge

    ContextForge is an open-source registry and proxy that federates MCP, REST, and gRPC services into a single, governed endpoint to simplify tool and API management for AI agents.

  • Project
    Haohao-end/openagent

    OpenAgent is a full-stack platform for building, orchestrating, and deploying AI agents, featuring a visual workflow editor, dataset management, and OpenAPI integration.