> browse/registry

> pgvector

Store and search vector embeddings in PostgreSQL with pgvector — no separate vector database needed. Use when someone asks to "vector search in Postgres", "store embeddings", "pgvector", "similarity search", "RAG with Postgres", "semantic search in existing database", or "add AI search to my app without a separate vector DB". Covers vector columns, indexing (IVFFlat, HNSW), similarity search, and integration with ORMs.

> d1-database

Build serverless applications with Cloudflare D1 — SQLite at the edge. Use when someone asks to "serverless database", "Cloudflare D1", "SQLite at the edge", "database for Workers", "edge database", or "serverless SQL". Covers schema setup, queries, migrations, Workers integration, and Drizzle ORM.

> aws-lambda

You are an expert in AWS Lambda, Amazon's serverless compute service. You help developers build event-driven applications using Lambda functions triggered by API Gateway, S3 events, SQS queues, DynamoDB streams, and scheduled events — with support for Node.js, Python, Go, Rust, Java, and container images, automatic scaling from zero to thousands of concurrent executions, and pay-per-invocation pricing.

> appwrite

Build backends with Appwrite — open-source Backend-as-a-Service. Use when a user asks to set up user authentication, manage a database without writing backend code, handle file storage and uploads, add realtime subscriptions, set up cloud functions, build a mobile or web app backend, replace Firebase with an open-source alternative, or self-host a BaaS platform. Covers auth, databases, storage, functions, realtime, and SDK integration for web, mobile, and server-side.

> traceloop

You are an expert in Traceloop and its OpenLLMetry SDK, the open-source observability framework that extends OpenTelemetry for LLM applications. You help developers instrument AI pipelines with automatic tracing for OpenAI, Anthropic, Cohere, LangChain, LlamaIndex, vector databases, and frameworks — exporting to any OpenTelemetry-compatible backend (Grafana Tempo, Jaeger, Datadog, Honeycomb, Traceloop Cloud).

> testcontainers

When the user wants to run integration tests with real dependencies using Docker containers managed by Testcontainers. Also use when the user mentions "testcontainers," "integration testing with Docker," "database integration tests," "containerized tests," or "test with real database." For API mocking without containers, see mockoon or wiremock.

> mongoose

You are an expert in Mongoose, the elegant MongoDB object modeling library for Node.js. You help developers define schemas with validation, build queries with a fluent API, use middleware hooks, populate references, create virtual fields, and handle transactions — providing structure and type safety on top of MongoDB's flexible document model.

> trigger-dev

You are an expert in Trigger.dev, the open-source background jobs platform for TypeScript. You help developers build reliable long-running tasks, scheduled jobs, webhook handlers, and event-driven workflows with automatic retries, concurrency control, real-time logs, and deployment to serverless infrastructure — replacing BullMQ/Redis setups with a fully managed or self-hosted solution purpose-built for modern TypeScript apps.

> airbyte

You are an expert in Airbyte, the open-source data integration platform with 300+ pre-built connectors. You help developers sync data from SaaS tools, databases, and APIs into data warehouses and lakes — handling incremental syncs, CDC (Change Data Capture), schema evolution, and error recovery for production data pipelines.

> electric-sql-sdk

You are an expert in Electric SQL, the sync engine that streams Postgres data to local apps in real-time. You help developers build local-first applications where data syncs from Postgres to client-side SQLite/PGlite automatically — enabling instant reads, offline support, and real-time multi-user collaboration using Postgres as the single source of truth with Shape-based partial replication.

> electric-sql

Build local-first applications with ElectricSQL — sync Postgres data to client devices in real-time. Use when someone asks to "sync database to client", "local-first app", "ElectricSQL", "offline-first sync", "real-time Postgres sync", "sync Postgres to SQLite", or "build an app that works offline". Covers shape-based sync, real-time subscriptions, offline support, and conflict resolution.

> elixir

You are an expert in Elixir, the functional programming language built on the Erlang VM (BEAM). You help developers build highly concurrent, fault-tolerant, and distributed systems using Elixir's process model, pattern matching, GenServer, supervision trees, Phoenix web framework, LiveView for real-time UI, and Ecto for database interactions — achieving massive concurrency with lightweight processes and "let it crash" reliability.

> grafana

Grafana is an open-source visualization and dashboarding platform that connects to dozens of data sources including Prometheus, PostgreSQL, ClickHouse, and Elasticsearch. It lets you build interactive dashboards with panels, set up alerting rules, and manage everything as code through JSON dashboard definitions and provisioning configuration.

> bull-mq

You are an expert in BullMQ, the high-performance job queue for Node.js built on Redis. You help developers build reliable background processing systems with delayed jobs, rate limiting, prioritization, repeatable cron jobs, job dependencies, concurrency control, and dead-letter handling — powering email sending, image processing, webhook delivery, report generation, and any async workload.

> lancedb

Embedded vector database with LanceDB — serverless, zero-config vector search for AI applications. Use when someone asks to "vector search without a server", "embedded vector database", "LanceDB", "local vector search", "serverless vector DB", "vector search in a file", or "lightweight RAG storage". Covers table creation, vector search, full-text search, hybrid search, and multimodal embeddings.

> rate-limiter

Designs and implements API rate limiting middleware and abuse protection. Use when you need to add request throttling, per-user quotas, IP-based blocking, sliding window or token bucket algorithms, Redis-backed distributed counters, or 429 response handling. Trigger words: rate limit, throttle, API abuse, too many requests, request quota, DDoS protection, brute force prevention, credential stuffing defense.

> llamaindex-ts

You are an expert in LlamaIndex.TS, the TypeScript data framework for building RAG (Retrieval-Augmented Generation) applications. You help developers ingest, index, and query data from any source — documents, APIs, databases — and connect it to LLMs with vector indexes, knowledge graphs, structured extraction, agents, and multi-document synthesis.

> neo4j

Neo4j is the leading graph database for connected data. Learn Cypher query language, node and relationship modeling, graph algorithms, and integration with Node.js using the official neo4j-driver.

> security-ownership-map

Analyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and export CSV/JSON for graph databases and visualization. Trigger only when the user explicitly wants a security-oriented ownership or bus-factor analysis grounded in git history (for example: orphaned sensitive code, security maintainers, CODEOWNERS reality checks for risk, sensitive hotspots, or ownership clusters). Do not trigger for general maintainer lists or n

> hashicorp-vault

Assists with managing secrets, encryption keys, and dynamic credentials using HashiCorp Vault. Use when configuring secret engines, setting up dynamic database credentials, implementing access policies, integrating with Kubernetes, or using Transit for encryption as a service. Trigger words: vault, secrets management, dynamic secrets, transit engine, pki, approle, vault agent.