InsForge: Open-Source Backend Platform for AI Coding Agents

InsForge (YC P26) is an open-source backend platform designed specifically for AI coding agents. Instead of agents juggling dashboards and manual config, InsForge gives them a CLI and skills to handle all backend/infra tasks end-to-end. The project is available on GitHub under Apache 2.0.
How It Works
Coding agents interact with InsForge through two interfaces:
- MCP Server (self-hosted and cloud): exposes InsForge operations as tools for any MCP-compatible agent.
- CLI + Skills (cloud only): a command line interface paired with Skills that agents invoke directly from the terminal.
Both allow agents to read backend context (docs, schemas, logs) and configure primitives (deploy edge functions, run migrations, create buckets, set up auth providers).
Core Products
- Authentication – user management, auth, sessions
- Database – Postgres relational database
- Storage – S3 compatible file storage
- Model Gateway – OpenAI compatible API across multiple LLM providers
- Edge Functions – serverless code on the edge
- Compute (private preview) – long-running container services
- Site Deployment – build and deploy sites
Agent-Specific Features
- Backend Branching: branch entire backend (DB, auth, storage, functions, schedules). Agents work on a branch, you review diffs, merge or discard. Inspired by Neon.
- Server Telemetry: agents read logs, CPU, memory, disk to find spikes and root causes.
- Debug Agent: every project gets a dedicated debug agent. Your coding agent asks questions like “why deployment fail?”, the debug agent runs diagnoses and proposes fixes.
- Backend Advisor: scans your backend daily for security and performance issues, proposes remediations, sends to your coding agent.
Quickstart (Self-Hosted)
git clone https://github.com/InsForge/InsForge.git
cd insforge
cp .env.example .env
docker compose -f docker-compose.prod.yml upThen open http://localhost:7130 to connect the MCP server. After setup, ask your agent: "I'm using InsForge as my backend platform."
Cloud version is available at insforge.dev.
The team notes they started InsForge because manual MCP setups had issues: tools pre-loaded into context, large payloads (>10k tokens), and missing capabilities like telemetry and configs. By putting everything into a CLI and teaching agents via skills, they avoided those problems.
📖 Read the full source: HN AI Agents
👀 See Also

CC-Canary: Detect Regressions in Claude Code with Local JSONL Analysis
CC-Canary reads Claude Code session logs and produces a forensic report on model drift, including read:edit ratio, reasoning loops, cost trends, and auto-detected inflection dates.

WhatsApp AI Assistant Built with Claude Code as OpenClaw Alternative
A developer built a WhatsApp AI assistant using Claude Code as the agentic brain, with a local relay server for WhatsApp webhooks and MCP server bridging. The project includes Arcade for scoped auth to Google Calendar, Gmail, and Slack.

FixAI Dev: A Consumer Rights Game Using Claude Haiku with Strict JSON Contracts
A developer built a browser game where Claude Haiku acts as a corporate AI denying consumer requests; players argue using real consumer protection laws across 37 cases in EU, US, UK, and Australia. The architecture uses Haiku for language only, with server-side game logic and strict JSON contracts between components.

Tokenmeter: Free Windows App to Track Claude Code Token Usage Offline
Tokenmeter is a free, open-source Windows app that reads local Claude Code .jsonl files to show token usage, estimated costs, cache savings, and a 90-day activity heatmap — all offline.