10 actions in 6 pieces of software · ranked by words, meaning and measured trust · 482 ms
modelrecord14,131 downloads/month
- text-generation
Task: text-generation
- text-generation
modelrecord44,845 downloads/month
- image-text-to-text
Task: image-text-to-text
- image-text-to-text
modelrecord
- text->text
Takes text; returns text.
- tool-calling
Can call tools (function calling).
- structured-outputs
Can return JSON matching a schema.
- text->text
modelrecord102,751 downloads/month
- tabular-classification
Task: tabular-classification
- tabular-classification
- 5exaone-cookbookfound in code, not yet checkedno passport yet
MCP serverlgai-research/exaone-cookbook
- source_diagnostics
Context7 / DuckDuckGo 사용 가능 여부, latency, API key 설정 상태를 진단한다.
- web_search
Context7 docs + DuckDuckGo web search를 병렬 조회한 통합 결과를 반환한다.
- extract_sources
`web_search` 결과(JSON 문자열 또는 `content` 텍스트)에서 citation을 구조화 추출한다.
- source_diagnostics
- 6aikofound in code, not yet checkedno passport yet
MCP serverjakubblunar/aiko
- force_misattunement
K23 — arm a one-shot bypass on the misattunement cooldown.
- force_misattunement
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.