Tag archive
solon-ai-harness is the orchestration container behind Solon AI agents — a rule engine, three interception strategies, and subagents defined as plain Markdown.
Most AI coding agents fail in the same way. Not with a wrong answer — with an incomplete one. They...
Your Java agent streams tokens. Your frontend speaks a protocol. Between them sits a translation...
In the multi-model era, your application already talks to more than one LLM: a cheap fast model for...
Every RAG pipeline starts the same way: you have stuff, and the model needs Documents. The...
Bocha, Baidu AI Search, and Tavily all sit behind the same Repository interface in Solon AI — and the same interface can turn search into an agent tool.
How the rerun and continue buttons in SolonCode's Web UI let you replay a conversation turn or extend the last response.
Most coding agents follow the same rhythm: you ask, they answer. You prompt again, they do another...
How Solon AI agents remember users across turns, servers and restarts - ChatSession, AgentSession, pluggable InMemory/File/Redis backends and windowed history.
If you build AI-powered applications on the JVM today, you will meet two frameworks quickly: Spring...
How to turn unstructured invoices, resumes and tickets into validated Java objects using type-driven JSON Schema generation in Solon AI - provider-agnostic and production ready.
Large Language Models (LLMs) are only as powerful as the tools they can access. While internal tools...