Local-first signal routing for AI coding agents
Native agents-router binary for macOS arm64
Native agents-router binary for Linux x64 GNU
Native agents-router binary for macOS x64
Native agents-router binary for Windows x64 MSVC
Simple middleware-style router
The tRPC Next.js library
Declarative routing for React
Modern and scalable routing for React applications
Nested/Data-driven/Framework-agnostic Routing
The tRPC server library
The tRPC client library
Modern and scalable routing for React applications
Select context for coding agents directly from your website
Modern and scalable routing for React applications
Declarative routing for React web applications
> To see what versions are currently supported, please refer to the [Security Policy](./packages/router/SECURITY.md).
Maps proxy protocols to `http.Agent` implementations
Expo Router is a file-based router for React Native and web applications.
TypeScript definitions for react-router-dom
Modern and scalable routing for React applications
OpenTelemetry instrumentation for `router` http middleware router
Modern and scalable routing for Web applications
Modern and scalable routing for React applications
RightAgent provides a foundation for running an agent on a server to interface in a secure fashion with other agents in the RightScale system using RightNet, which operates in either HTTP or AMQP mode. When using HTTP, RightAgent makes requests to RightApi servers and receives requests using long-polling or WebSockets via the RightNet router. To respond to requests it posts to the HTTP router. When using AMQP, RightAgent uses RabbitMQ as the message bus and the RightNet router as the routing node to make requests; to receives requests routed to it by the RightNet router, it establishes a queue on startup. The packets are structured to invoke services in the agent represented by actors and methods. The RightAgent may respond to these requests with a result packet that the router then routes to the originator.
pikuri-vectordb gives a pikuri-core agent a +vectordb_search+ tool over a local document corpus — agentic search, the agent decides when to retrieve. Ships a swappable backend (a pure-Ruby +Backend::InMemory+ for teaching, plus thin +Backend::Qdrant+ / +Backend::Chroma+ HTTP clients for persistence — Qdrant recommended), a chunker, an embedder wrapper over +RubyLLM.embed+, and an optional +Reranker::LlamaServer+ that speaks +/v1/rerank+ against a cross-encoder model. Text extraction goes through +Pikuri::FileType.read_as_text+ in pikuri-core, which handles plain text / Markdown / PDF; HTML extraction is a deferred follow-up. Hosts wire the feature via +c.add_extension Pikuri::VectorDb::Extension.new(...)+ inside the +Agent.new+ block — same opt-in shape as +pikuri-tasks+ / +pikuri-skills+. The bundled +Pikuri::VectorDb::LIBRARIAN+ persona is the privilege-separated sub-agent counterpart for hosts that want recall to flow through a child rather than the parent's context. Three model endpoints in the full setup — chat (via ruby_llm), an embedder (via +RubyLLM.embed+), and an optional reranker (HTTP +/v1/rerank+). A single +llama-server+ in router mode serves all three by default, loading each cached GGUF on demand; see the gem's README for details.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.