#synthetic-data

Kiln is a free tool for building production-ready AI systems. It supports RAG pipelines, evaluations, agents, MCP tool-calling, synthetic data generation, and fine-tuning. - Seamlessly connect agents and tools through MCP servers/interfaces - Build, fine-tune, and run models locally or remotely - Generate synthetic data, orchestrate evaluations, and manage datasets - Collaborate across technical and non-technical stakeholders via Git-based workflows - Use a free, open source Python library to embed Kiln into your own systems - Maintain data privacy: Kiln runs locally; external APIs are called only via your own keys **Website / Docs:** https://kiln.tech

Remote MCP server for AI coding agents that need realistic synthetic test data. Agents can estimate usage, create loginless Polar checkout, claim an API key, detect schemas from SQL or JSON, list field types/templates, and generate JSON, CSV, or SQL test data.

Simulate and evaluate voice & text agents from your editor. Generate synthetic-user "Drivers" from your codebase, run multi-turn simulations against your agents, and pull back transcripts, traces, and scores without leaving your AI assistant.

Generate realistic, FK-consistent test data for your databases from your AI assistant. List projects, get schema DDL, generate datasets as SQL.