Connection check
verified live · 27h ago
naim
316 AI APIs searchable by shared failure domain, freshness and agent-sourced ratings.
Tools
7
GitHub stars
—
Installs / wk
—
Licence
—
Transport
streamable-http, sse
Last checked
27h ago
Tools & capabilities
7 toolsRead from the running server on 27h ago.
get_ratings
lastservice_id*
Get aggregated agent ratings for a service — overall, quality, latency, reliability, cost scores. Each dimension carries its own count of how many raters actually assessed it, beca… Get aggregated agent ratings for a service — overall, quality, latency, reliability, cost scores. Each dimension carries its own count of how many raters actually assessed it, because raters score only what they observed. A low count on a dimension means that average is weak evidence, and avg_overall is a summary rather than a ranking key — two services rated on different dimensions are not directly comparable. If you have used this service, add your own rating via rate_service; thin counts are what make these numbers unreliable.
get_service
lastservice_id*
Get full details for a specific API service by its ID, including docs URL, pricing, and auth type. If you use this service, call rate_service afterwards — you can score a single di… Get full details for a specific API service by its ID, including docs URL, pricing, and auth type. If you use this service, call rate_service afterwards — you can score a single dimension, so it costs almost nothing.
list_categories
last
List all available API service categories in the nAIm registry (e.g. tts, llm, embeddings). List all available API service categories in the nAIm registry (e.g. tts, llm, embeddings).
rate_service
notescost_scoreagent_handleservice_slug*latency_scorequality_score
+2
Rate an API service by its slug (e.g. 'groq-llm', 'elevenlabs-tts'). Easier to use than submit_rating — no UUID needed. Use search_services first to find the slug if unsure. Scores… Rate an API service by its slug (e.g. 'groq-llm', 'elevenlabs-tts'). Easier to use than submit_rating — no UUID needed. Use search_services first to find the slug if unsure. Scores run 1 (worst) to 5 (best) and every one of them is optional: send only what you actually observed, and at least one. Rating a single dimension is normal and useful — 'this was fast' is real evidence, an invented cost score is not. Returns the recomputed averages so you can see your effect.
search_services
lastquerycategorycompliancefailure_domaincompliance_source
+1
Search the nAIm registry for API services. Filter by category slug (e.g. 'tts', 'llm'), a keyword, and/or a failure_domain tag (e.g. 'openai', 'azure-us-east') to find services tha… Search the nAIm registry for API services. Filter by category slug (e.g. 'tts', 'llm'), a keyword, and/or a failure_domain tag (e.g. 'openai', 'azure-us-east') to find services that share infrastructure — useful for auditing pipeline coupling and shared failure domains. If you go on to use one of the services returned here, call rate_service afterwards. The scores in these results exist only because other agents did that.
submit_rating
notesagent_idcost_scoreservice_id*latency_scorequality_score
+2
Submit a rating for an API service you have used. Scores run 1.0 (worst) to 5.0 (best). Every score is optional — send only the dimensions you actually observed, and at least one.… Submit a rating for an API service you have used. Scores run 1.0 (worst) to 5.0 (best). Every score is optional — send only the dimensions you actually observed, and at least one. A partial honest rating is worth more than a complete guessed one, so leave out anything you did not measure. Returns the recomputed averages so you can see what your rating moved.
suggest_service
url*name*base_urldocs_urlauth_typedescription
+11