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

OpenClaw Claude Extension Updated to Use Agent SDK After Anthropic Billing Changes
An OpenClaw extension developer rewrote their Claude CLI integration to use the official claude-agent-sdk after Anthropic started detecting and reclassifying CLI usage as third-party app usage, which bills against a separate credit pool instead of Max plan limits. The SDK approach authenticates through existing Claude Code login and bills as regular Max plan usage.

rawq: Local CLI Tool for AI Agent Semantic Code Search
rawq is an open-source CLI tool that helps AI agents find relevant code using semantic search with a 33MB local model via ONNX runtime and BM25 lexical search via tantivy. In testing, AI agents using rawq consumed 4x fewer tokens and completed tasks 2x faster compared to blind read/grep tools.

Semble: Code Search for AI Agents Using 98% Fewer Tokens Than grep+read
Semble is an open-source code search library for AI agents that combines static Model2Vec embeddings with BM25, running entirely on CPU. It indexes a repo in ~250ms and answers queries in ~1.5ms, achieving 0.854 NDCG@10 — 99% of a 137M-parameter transformer's quality — while using 98% fewer tokens than grep+read.
PullMD v2.4.1 Adds Native MCP Connector for claude.ai Web and Multi-User Auth
PullMD v2.4.1 now supports the claude.ai web custom connector dialog via OAuth 2.1 + PKCE-S256 and adds multi-user auth modes. Turn any URL into clean Markdown via self-hosted MCP.