tool calls

Self-hosted LLM proxy that redacts personal data before requests reach model providers, including inside tool-call arguments and multimodal content. It supports OpenAI-compatible clients, runs locally with zero telemetry, and uses Presidio plus an optional privacy filter for broader PII and secret detection.

Open-source SDK for governing AI agent tool calls before side effects happen, with policy enforcement, approval flows, audit logs, and local execution.

A Ruby gem that encodes the Vercel AI SDK Data Stream protocol for Rails and Rack backends, so Ruby apps can stream text, reasoning, tool calls, and data parts to useChat/useObject.

A technical case study on reducing token usage in a coding agent, including a model-free harness, wire-level measurement, and several concrete optimizations that cut a long run from 1.04M to 517k tokens.