A minimal, notebook-first framework for running reproducible LLM experiments and comparing multiple models over JSONL/CSV datasets.
Cross-referenced across 55 tracked directories
#21670
Popularity Rank
1 / 55
Listed In
Emerging
Adoption Stage
3d
Listed For
1
Contributors
0
GitHub Stars
0
Forks
1
Contributors
vercel-release-bot
Detect if code is running in an AI agent or automated development environment
GitHub Actions
OpenInference utilities for ingesting Vercel AI SDK spans
ashishbansal
Playwright integration for ModelContext
awkoy
MCP for Notion
11/15/2025
Last Commit
Recently added to the ecosystem
Failed to load scan configuration.