emmimal
2 prompts
#Type
- 1context-engineA pure-Python context management layer for LLM systems — retrieval, re-ranking, memory decay, and token-budget enforcement in one pipeline.PromptsMay 2026
- 2prompt-pruning-layerA deterministic, zero-dependency prompt-pruning layer for long-running LLM conversations — expires stale tool state, collapses duplicate context, and proves it never drops a fact a later turn still depends on.PromptsJul 2026
