core of chat app
AI Chat Core - HybridAgent with Doubao + Gemini
Nextclaw agent chat core library.
```js import ChatCore from '@ideabosque/chat-core';
scuttlebutt chat core
`@dittolive/ditto-chat-core` is a React and TypeScript-based library leveraging Ditto for real-time chat functionalities.
Reusable AI Chat core for WordPress modules
Chat core library with MongoDB and Redis support
Chat core logic for Optima gateway - Provider, hooks, store, WebSocket client
DEPRECATED: use @teodor/chat-core and @teodor/chat-ui
breeze chat core
Platform-agnostic core for Antz Chat — API, socket, stores, types. Works in browser, React Native (Expo or bare), and Node.js.
Chat 核心能力包。
Pure React chat UI for Lace Cloud. Takes a `WebviewBridge` (postMessage-shaped) and renders the chat experience. Re-exports protocol types from `@lace-cloud/chat-core`.
Typescript Networking Library for the Yext Chat API
Svelte reference UI package for @sentropic/* chat sessions: stream rendering, optimistic client state, local-tool handoff, renderer registry, and host adapter contracts. Consumes @sentropic/chat-core wire contracts over HTTP/SSE only.
Accessibility engine for automated Web UI testing
Transport-agnostic streaming chat core — robust SSE parser, request-scoped state machine, first-class agent/tool/RAG metadata.
The CommonMark markdown constructs
Real-time community chat primitives for Relaya™ — TypeScript types, REST API client, WebSocket connection manager. Connects to the Relaya™ SaaS at api.relaya.chat. Works in browser and React Native.
Transport-agnostic message reducer and types for Jack chat (desktop + mobile).
Core library for multi-provider LLM chat interactions
OpenAI integrations for LangChain.js
core Besida module with base functional set for chat
Core library for chat-rs
Provider implementation of OpenAI for chat-rs
Cerebras Inference provider for chat-rs.
Provider implementation of Claude for chat-rs
Generic OpenAI-compatible Chat Completions client for chat-rs. Bring your own server (Ollama, vLLM, llama.cpp, LiteLLM, etc.).
DeepSeek provider for chat-rs.
Provider implementation of Gemini for chat-rs
Hugging Face Inference Providers (Router) for chat-rs.
Local-inference provider for chat-rs, built on mistral.rs.
Ollama provider for chat-rs (OpenAI-compatible endpoint).
OpenRouter provider for chat-rs (OpenAI-compatible Responses API).
Generic OpenAI Responses API client for chat-rs. Bring your own server.
pikuri-core is the lean, audit-friendly foundation of the pikuri family: Pikuri::Agent (a thin wrapper around ruby_llm's chat loop) with its Configurator + Extension protocol, the strict Pikuri::Tool framework, a listener surface for rendering / budgets / sub-agents, and four bundled stateless tools (calculator, web search, web scrape, fetch). Extensions (skills, MCP, workspace, coding stack, named-agent personas) live in sibling gems so a privacy-conscious user can install just this core and audit a minimal dependency tree. For the convenience bundle that pulls in everything, see the +pikuri+ metagem.
Adds Pollinations AI support to RubyLLM — chat, image/video generation, TTS/music, and transcription via the Pollinations API. Installs as a standalone gem without modifying RubyLLM core.
pikuri-assistant ships the demo +bin/pikuri-assistant+ binary on top of pikuri-core + pikuri-skills + pikuri-mcp: an interactive chat agent the user hand-edits to declare a +Pikuri::Mcp::Registry+ of MCP servers. The +Pikuri.prompt+ search path picks up this gem's +prompts/pikuri-assistant.txt+ automatically on require — same multi-gem prompt-dir pattern as pikuri-code.
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.
pikuri-memory gives a pikuri-core agent durable, long-lived memory: facts about the user and their work that persist across conversations. It wires a +recall+ tool plus an automatic per-turn prefetch onto an agent via +c.add_extension Pikuri::Memory::Extension.new(...)+ inside the +Agent.new+ block — same opt-in shape as +pikuri-tasks+ / +pikuri-vectordb+. Recall is automatic and synchronous (embed + vector search, milliseconds); capture is automatic and asynchronous (an off-the-interaction-path extraction queue), so a turn never blocks on "what should I remember?". Storage is mem0 (https://github.com/mem0ai/mem0) reached over a thin Faraday HTTP client — the append-only +add+ / read-time +search+ model. Only the *user's own words* are fed to extraction (a write-side hygiene rule that structurally drops system/assistant/tool-sourced junk), and recalled context enters the chat as a +:system+ message so it is provenance-tagged and excluded from the next extraction pass. This release ships the Ruby client + extension + tool against a *bring-your-own* mem0 endpoint; a self-managed mem0 sidecar supervisor (the +ChromaServer+-style docker pattern) is a follow-on.
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.
No description provided.
No description provided.