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

ClaudyBro: Native macOS Terminal for Claude Code Workflows
ClaudyBro is a 3.5 MB native Swift terminal app built specifically for Claude Code users, featuring image paste, process inspection, orphan cleanup, and smart MCP management. It uses 68 MB memory idle and 82 MB with Claude running.

Throttle Meter: Open-Source Claude Code Usage Meter for macOS
Open-source macOS menu bar app that reads local Claude Code logs to show real-time 5-hour and weekly usage, with threshold notifications and token-saving hooks. Also has a €19 commercial sibling with Exact mode (reads claude.ai's internal API via Safari).

Eä: A SIMD Compiler for Python Written in Rust
A developer built Eä, a compiler for SIMD kernels in ~12k lines of Rust that generates shared libraries and Python wrappers from .ea files, achieving 6.6× speedups over NumPy without ctypes or build systems.

CAL: Open-Source Context Optimization Layer for LLM Agents
CAL (Context Assembly Layer) is a Python library that reduces Claude API token usage by 83% through intelligent context selection and compression. It's available via pip install and MIT licensed.