agent-convergence-scorer
by Community
CLI and Python library for lexical stability checks on repeated short agent outputs: pairwise exact agreement, token overlap, divergence point, and an order-independent score. Zero
OSS
agent-convergence-scorer
Added 16 Oct 2026
Overview
A CLI and Python library for checking lexical stability of repeated short agent outputs. It computes pairwise exact agreement, token overlap, divergence point, and an order-independent score. Has zero runtime dependencies.
Best for
Best for
Developers who need quick lexical consistency checks on short LLM or agent outputs.
Use cases
- Compare repeated agent outputs for exact or token-level agreement
- Identify the point where two responses diverge
- Score output consistency independent of token order
Notes
0 stars on GitHub. Last updated 2026-09-28. Licensed MIT.
Pros
- Zero runtime dependencies makes it easy to install and run
- Provides multiple lexical metrics in one tool
- Simple CLI suitable for scripting and CI checks
Cons
- Lexical only, so it misses semantic similarity
- Designed for short outputs, not long documents
- Community project with no stars or release history yet
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.