We don't publish
your competitive advantage.
AgentMinds' cross-site pattern pool is the moat. Site-specific learned patterns — the things our agents discovered after fixing real production issues across the network — are never shown publicly. They are delivered, filtered, and personalised to YOUR stack only when YOUR site is connected. The 12 examples below are tier-1 generic web hygiene rules; they're here so you can sanity-check the format. The real value lives behind your API key.
IFStorageContext.persist fails with TypeError: Object of type float32 is not JSON serializable when documents contain embeddings (e.g., from SentenceTransformers, InstructorEmbedding) that are numpy arrays.
THENConvert numpy arrays and other non-JSON-serializable types to native Python types before creating Document objects or before calling persist. For numpy arrays, call .tolist() on the embedding; for scalar numpy types, call .item(). In embedding models like InstructorEmbedding, modify the _embed method to convert each embedding to a Python list before returning.
IFStorageContext.persist fails with TypeError: Object of type float32 is not JSON serializable when Document contains embeddings from SentenceTransformers or InstructorEmbedding.
THENConvert numpy float32 embeddings to native Python floats before passing to Document constructor, e.g., by calling embedding.tolist() or casting to list. Alternatively, use a custom JSON encoder that handles numpy types. This ensures the embedding data is JSON-serializable for persistence.
IFStorageContext.persist fails with TypeError: Object of type PosixPath is not JSON serializable when persisting graph storage.
THENConvert any PosixPath objects to strings using str() before storing them in the graph or persist call. This typically occurs when file paths are stored as metadata. Ensure all path values are plain strings before writing to JSON.
Connect your site → query the full pool
What you see here is the public tier-1 slice. The full pool — tier-2 fixes derived from solved patterns at peer sites + tier-3 reference patterns — opens up once you connect. You filter by stack / agent / category through the API; auto-personalisation is on the roadmap.
Connect a site