A rule-based command-output optimization and context-compression layer that reduces unnecessary LLM context while preserving important information.
MCP server that preserves decisions and context across AI coding sessions
Jendrik Jördening shares practical engineering strategies for integrating LLMs into production pipelines. He discusses overcoming non-determinism, restricting schemas, separating semantic text extraction from deterministic code, and validating choices using d…
Comet tool for logging and evaluating LLM traces
With more patches per month than at a pirate convention, the bug must be an endangered species. Well, about that
