10 actions in 10 pieces of software · ranked by words, meaning and measured trust · 529 ms
modelrecord11,249 downloads/month
- fill-mask
Task: fill-mask
- fill-mask
modelrecord813,832 downloads/month
- translation
Task: translation
- translation
modelrecord14,164 downloads/month
- image-text-to-text
Task: image-text-to-text
- image-text-to-text
modelrecord385,418 downloads/month
- automatic-speech-recognition
Task: automatic-speech-recognition
- automatic-speech-recognition
modelrecord1,702 downloads/month
- text-ranking
Task: text-ranking
- text-ranking
skillk-dense-ai/scientific-agent-skillsrecord
- esm
Uses the Biohub esm Python SDK for ESM3 protein generation, ESMC embeddings, and ESMFold2 all-atom folding. Applies to local model inference and Biohub hosted clients, including former Forge workflows; distinguishes the separate legacy fair-esm distribution.
- esm
- 7Bhili ASR (Conformer 600M)demo or tutorialno passport yet
MCP serverrecord
- bhili_asr_conformer_transcribe
Transcribe Bhili speech to Devanagari text (CTC decoding). If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool
- bhili_asr_conformer_transcribe
MCP serverrecord
- pronmt_context_mt_demo_translate
Translate an English sentence into German with three NLLB-600M checkpoints. Returns: The baseline translation, the ProNMT (no-context) translation, the, ProNMT context-aware translation, and a markdown pronoun report.
- pronmt_context_mt_demo_translate
- 9qsearchfound in code, not yet checkedno passport yet
- sweep_context
Brave LLM Context endpoint analogue using local Qwen3-600M ($0 cost, GPU only). Fetches HTML, strips boilerplate, extracts facts/numbers/quotes per URL. Use for Phase 4 deep read when Brave Context quota is tight.
- sweep_context
- 10sigen-mcpfound in code, not yet checkedno passport yet
MCP serverpaulczar/sigen-mcp
- read_ems_mode
Read and decode the current EMS operating mode
- read_ems_mode
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.