10 actions in 10 pieces of software · ranked by words, meaning and measured trust · 671 ms
modelrecord14,421 downloads/month
- sentence-similarity
Task: sentence-similarity
- sentence-similarity
modelrecord746,658 downloads/month
- fill-mask
Task: fill-mask
- fill-mask
modelrecord64,917 downloads/month
- text-generation
Task: text-generation
- text-generation
modelrecord2,915 downloads/month
- text-classification
Task: text-classification
- text-classification
modelrecord
- sharaddition/paraphrase-gpt
T5 model fine tuned on GPT-3.5 generated paraphrase corpus of 6.3 million unique sentences.
- sharaddition/paraphrase-gpt
- 6GLiFormer Large v1demo or tutorialno passport yet
MCP serverrecord
- gliformer_large_v1_demo_rank_by_similarity
Rank candidate texts against a query using the model's embedding head. Returns: A ranked candidate/cosine-similarity table and the raw ranking JSON.
- gliformer_large_v1_demo_rank_by_similarity
- 7AsterMind MCPfound in code, not yet checkedno passport yet
MCP serverAsterMindAI/astermind-mcp
- compare_texts
Cosine similarity (0..1) between two texts using local embeddings. Best for detecting near-duplicates / paraphrase overlap, not fine-grained semantic ranking.
- compare_texts
- 8ollama-almasrv-mcpfound in code, not yet checkedno passport yet
MCP servervankasins/ollama-almasrv-mcp
- ollama_similarity
Calculate cosine similarity between two texts using ALMASRV embeddings (mxbai-embed-large 1024-dim).
- ollama_similarity
- create_paraphrase
Create Paraphrase — Rewrite text while preserving its meaning.
- create_paraphrase
- 10jsonld-exfound in code, not yet checkedno passport yet
MCP serverjemsbhai/jsonld-ex
- cosine_similarity
Compute cosine similarity between two embedding vectors.
- cosine_similarity
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.