Logo
Deploy Now

SaaS Alternative

Vercel Netlify Supabase Firebase

Categories

Developer Tools Database Authentication MCP Backend as a Service Serverless AI Infrastructure

Stars

12,761

Forks

1,154

Watchers

35

Developer links

Last Updated: 08-21-2026 01:21 PM (UTC)

InsForge

With 12,600 GitHub stars and 52 releases in under a year of development, InsForge is the fastest-growing open-source backend platform purpose-built for AI coding agents — giving Claude, Cursor, and any MCP-compatible tool direct access to database, authentication, storage, compute, and AI model infrastructure through a single self-hosted stack. The native MCP server exposes every InsForge operation as callable tools, letting coding agents autonomously create database tables, manage user authentication, upload files, deploy edge functions, and ship complete full-stack applications without human intervention. The Model Gateway provides an OpenAI-compatible API that routes requests across multiple LLM providers (OpenAI, Anthropic, Google, and open-source models) with unified billing, rate limiting, and fallback logic. PostgreSQL with pgvector handles both relational data and vector embeddings for RAG pipelines, while S3-compatible storage manages file uploads and static assets. Edge Functions run serverless TypeScript code on Deno with sub-millisecond cold starts for API endpoints, webhooks, and scheduled tasks. The authentication system provides user management, OAuth2 flows, sessions, and magic links with JWT token handling built in. Site Deployment builds and serves frontend applications with automatic SSL and custom domain configuration. The CLI paired with Agent Skills enables terminal-based workflows where agents invoke InsForge operations directly from the command line. Deploy via Docker with PostgreSQL as the only required external dependency. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

InsForge
InsForge
InsForge
InsForge
InsForge

Benefits

  • AI Agents Ship Full Applications
  • MCP server exposes database, auth, storage, and deployment as callable tools so coding agents autonomously build and ship complete applications without manual infrastructure setup.
  • Unified LLM Model Gateway
  • OpenAI-compatible API routes requests across multiple LLM providers with unified rate limiting, fallback logic, and usage tracking through a single endpoint configuration.
  • Complete Backend In One Platform
  • PostgreSQL database, user authentication, S3 storage, edge functions, compute containers, and site deployment replace multiple infrastructure services with one self-hosted stack.
  • Vector Search For RAG Pipelines
  • pgvector extension enables semantic search and retrieval-augmented generation directly in PostgreSQL without requiring separate vector database infrastructure or data duplication.

Features

  • MCP Server Integration
  • Exposes all InsForge operations as MCP-compatible tools that Claude, Cursor, and other AI agents call directly to manage infrastructure autonomously.
  • PostgreSQL With pgvector
  • Relational database with vector embedding support for semantic search, RAG pipelines, and hybrid queries combining structured and unstructured data.
  • Model Gateway
  • OpenAI-compatible API routing to multiple LLM providers with unified authentication, rate limiting, usage tracking, and automatic fallback between models.
  • Edge Functions
  • Serverless TypeScript code running on Deno with fast cold starts for API endpoints, webhooks, scheduled tasks, and custom backend logic.
  • Authentication System
  • User management with OAuth2, magic links, JWT sessions, role-based access control, and social login providers for complete identity infrastructure.
  • Site Deployment
  • Frontend build and deployment with automatic SSL certificate provisioning, custom domain configuration, and CDN-ready static asset serving.