Show HN: InsForge – An Open-Source Heroku for Coding Agents

InsForge is an all-in-one backend platform designed specifically for AI coding agents. It provides database, authentication, storage, compute, hosting, and an AI gateway so agents can build full-stack apps end to end.

Agents interact with InsForge through two interfaces:

• MCP Server (self-hosted and cloud): provides InsForge features as tools that MCP-compatible agents can call
• CLI + Skills (cloud): a command-line interface that agents run directly from the terminal

Agents can operate the platform like a backend engineer. They read backend context such as documentation, schemas, lists of deployed functions, and runtime logs, and directly configure backend resources — deploying edge functions, running database migrations, creating storage buckets, and setting up auth providers.

Key services offered:

• Authentication: user management and sessions
• Database: Postgres relational database
• Storage: S3-compatible file storage
• Model Gateway: an OpenAI-compatible API unifying multiple LLM providers
• Edge Functions: serverless code execution
• Compute (private preview): long-running container services
• Site Deployment: site build and deployment

Local self-hosting is available via Docker Compose, and a cloud-hosted version is also offered at insforge.dev. One-click deployment options are supported on Railway, Zeabur, and Sealos. It is released under the Apache 2.0 license, with a Discord community and detailed documentation available.