Node.js library for LastMile AI Semantic Retrieval Framework
Vector similarity search over gRPC — semantic retrieval without a dedicated database per product.
Open-source memory engine for AI applications — semantic retrieval, AUDN mutation, and contradiction-safe claim versioning.
Infinite context windows for Claude via OpenMemory semantic retrieval
Semantic code retrieval MCP Server — natural language → relevant code snippets, with incremental sync and file watching
Lightweight local semantic retrieval enhancement for the Bamdra OpenClaw memory suite.
MCP server for product.md — semantic retrieval over .product/ specs with citation-rich answers.
Codex-native scientific research assistant for scholarly search, library management, full-text analysis, and local semantic retrieval
SharkCraft local-first semantic retrieval, plan cache, declaration extractor, and task classifier.
Graph-based semantic retrieval without embeddings - replaces vector DBs
Advanced memory management system for AI agents with semantic retrieval, hierarchical structures, and multi-agent support
OpenTelemetry semantic conventions
The official Pinecone TypeScript SDK for building vector search applications with AI/ML.
Automated semver compliant package publishing
errors with more than just a message
semantic-release plugin to publish a GitHub release and comment on released Pull Requests/Issues
AdiaUI A2UI retrieval layer — catalog lookup, intent classification, domain routing, pattern + anti-pattern matching, clarity + context assembly. Consumed by the compose engine and any A2UI-protocol tooling that needs to reason about user intent against t
semantic-release plugin to publish a npm package
semantic-release plugin to commit release assets to the project's git repository
semantic-release plugin to generate changelog content with conventional-changelog
The semantic version parser used by npm.
semantic-release plugin to analyze commits with conventional-changelog
semantic-release plugin to create or update a changelog file
Binary plugins to supercharge @cdxgen/cdxgen npm package
This gem provides out-of-the-box functionality for generating vectors using the OpenAI API's text-embedding-ada-002 model and uploading them to Pinecone for efficient semantic search. It also includes features for querying existing vectors and retrieving relevant metadata. With this gem, developers can easily incorporate semantic search capabilities into their Ruby applications without needing to worry about the underlying implementation details.
A powerful tool for RAG (Retrieval-Augmented Generation) that splits text into chunks based on semantic meaning rather than just character counts. Supports sliding windows, adaptive buffering, and dynamic percentile-based thresholding.
Models spreading activation in semantic networks - priming one concept activates related concepts with distance-based decay for rapid associative retrieval.
POSEIdON (short for “Pimp your Objects with SEmantic InformatiON”) is a small library that lets you add RDF information to classes and their instances. It can also add methods as_rdf and to_rdf to those classes and objects that can be used to retrieve RDF representations in various formats, based on the functionality provided by the RDF gem.
Tulving semantic memory store for brain-modeled agentic AI — concept storage, taxonomic relations (is_a, has_a, part_of), spreading activation retrieval, and knowledge consolidation with confidence-based decay.
== OceanDynamo As one important use case for OceanDynamo is to facilitate the conversion of SQL databases to no-SQL DynamoDB databases, it is important that the syntax and semantics of OceanDynamo are as close as possible to those of ActiveRecord. This includes callbacks, exceptions and method chaining semantics. OceanDynamo follows this pattern closely and is of course based on ActiveModel. The attribute and persistence layer of OceanDynamo is modeled on that of ActiveRecord: there's +save+, +save!+, +create+, +update+, +update!+, +update_attributes+, +find_each+, +destroy_all+, +delete_all+, +read_attribute+, +write_attribute+ and all the other methods you're used to. The design goal is always to implement as much of the ActiveRecord interface as possible, without compromising scalability. This makes the task of switching from SQL to no-SQL much easier. OceanDynamo uses only primary indices to retrieve related table items and collections, which means it will scale without limits. OceanDynamo is fully usable as an ActiveModel and can be used by Rails controllers. Thanks to its structural similarity to ActiveRecord, OceanDynamo works with FactoryBot. See also Ocean, a Rails framework for creating highly scalable SOAs in the cloud, in which ocean-dynamo is used as a central component: http://wiki.oceanframework.net
Provides RobotLab::DocumentStore — a thread-safe, in-memory semantic search store backed by fastembed (BAAI/bge-small-en-v1.5). Store text documents by key and retrieve the closest matches to a natural-language query using cosine similarity. Works standalone or as a drop-in extension for robot_lab agents and networks.
This is the Songtradr API. Use it to retrieve deep music metadata and trigger processes like auto-tagging. You can also use the API to manage your account and musicube cloud data. **Authentication** 1. Reach out to support@songtradr.com to receive a free account or use your login data if you are already signed up. 2. To authenticate, you need to login via the POST /api/v1/user/login endpoint. 3. The endpoint responds with a jwtToken which you can use in all following API requests as a bearer token. **Rate Limiting** The current limit is 120 Requests per minute. Reach out to us via support@songtradr.com if you need to request more. **Getting Started with auto-tagging** 1. If you want to get your own files auto-tagged, use the POST /api/v1/user/file/{name}/initUpload endpoint. It responds with a presigned S3 link where you can upload your file. 2. You can check the processing status of your file via the GET /api/v1/user/file/{name}/filesStatus endpoint. 3. As soon as processing is done, you can request the generated data via the GET /api/v1/user/files endpoint. **Getting Started with search** You can either search the released music via the /public/recording endpoints or your own private uploaded music via the /user/file/ endpoints. 1. If you want to search the world's released music, a good starting point is the GET /api/v1/public/recording/search endpoint. Please find the extensive list of parameters that serve as semantic search filters. 2. If you want to search your own previously uploaded music, a good starting point is the GET GET /api/v1/user/files endpoint. It has the same extensive list of parameters that serve as semantic search filters.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.