~/ / Build with AI APIs and agents
Tools for before and after you call an AI API. Count tokens and estimate the cost, hide secrets before you paste, check structured-output schemas, tool definitions and MCP configs, and repair the JSON a model returns.
No powerful PC? Rent a VPS and run a small local LLM from your browser: six steps from memory estimate to a protected chat screen, with the limits stated honestly.
Published: Tools you can use: Local LLM Memory Estimator, LLM API Cost Calculator
Constrain a local model's output with a JSON Schema and call Ollama from OpenAI-style clients: what the official docs say, and what is not supported.
Published: Tools you can use: JSON Schema Validator, LLM JSON Repair, Ollama OpenAI Converter
Planning to run Ollama or Dify on a VPS? What the official docs say about memory, CPU-only inference and the ports to keep closed.
Published: Tools you can use: LLM API Cost Calculator
GitGuardian found 2,117 valid credentials in public MCP config files. What the report says, how to keep secrets out of yours, and tools to check.
Published: Tools you can use: MCP Config Checker, Prompt Redactor
MCP specification 2026-07-28 makes the protocol stateless and deprecates HTTP+SSE and more. What changed, and how to check your config and tool schemas.
Published: Tools you can use: MCP Config Checker, JSON Schema Validator