4 packages found
Measure and improve the token-efficiency of agent-facing APIs (OpenAPI & MCP): a scorer, linter, the LAP profile, and a
Compression with a quality contract — cache-aware, causally-pruned LLM context compression for agentic runtimes, certifi
Git-first memory for AI agents: Markdown files are truth, the index is disposable, writes are reviewable commits.
MCP server that scores text and landing-page copy for AI-writing style tells. Deterministic, offline, no LLM call, no ne