Browse executable AI solution packages
Search by use case, stack, or implementation problem. Each product is built around source code, local run steps, and verification evidence.
A semantic cache changes the serving contract. Instead of sending every request to the model, the application first asks whether a prior answer is similar enough, fresh enough, and safe enough to reuse.
A runnable prompt management service that versions prompt templates in PostgreSQL, routes live traffic between control and candidate variants using weighted canary splits, evaluates outputs with deterministic and LLM-as-judge scorers, and auto-promotes or auto-rolls-back based on statistical significance.
A runnable MCP server and client pair built with Spring AI 1.1.x that exposes domain tools via @McpTool, connects over Streamable HTTP transport, and supports dynamic tool registration without service restart.
A runnable event-driven pipeline that enriches Kafka messages using LLM calls with idempotent processing, DLQ handling, and end-to-end tracing.
A runnable chat service that streams LLM tokens over SSE, supports cancellation and resume, and persists conversation state safely.
A production-grade LLM proxy that enforces per-tenant API keys, rate limits, token budgets, caching, and audit logging.