Sources

lanista aggregates data from these catalogs and community feeds. Live sources are fetched on each startup; curated sources ship as seed files.

Community feeds

Practitioner opinions — blog posts and discussions — fetched and cached by lanista refresh-opinions. Used to ground LLM recommendations in real-world usage reports.

willison https://simonwillison.net/tags/llms.atom feed

eugeneyan https://eugeneyan.com/rss/ feed

hn https://hn.algolia.com/api/v1/search feed

✦

Catalog sources

openrouter https://openrouter.ai/api/v1/models live

litellm https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json live

pimono https://raw.githubusercontent.com/badlogic/pi-mono/main/packages/ai/src/models.generated.ts live

gkisokay seed file curated

factory_weather https://factory.strongdm.ai/weather-report/feed.xml live

aider https://raw.githubusercontent.com/Aider-AI/aider/main/aider/website/_data/polyglot_leaderboard.yml live

artificial_analysis seed file curated

lmarena https://huggingface.co/api/datasets/lmarena-ai/leaderboard-dataset/parquet live