Agent chat components
A TypeScript client for the Agent Chat messaging API
Reusable Nextclaw agent chat UI primitives and default skin.
Nextclaw agent chat core library.
A React conversational agent chat component
TypeScript library for integrating with Jiva.ai Agent Chat API
agent-chat binary for darwin/amd64
A React component library for building AI agent chat interfaces.
agent-chat binary for windows/arm64
agent-chat binary for darwin/arm64
agent-chat binary for linux/amd64
agent-chat binary for linux/arm64
Bot Swarm Agent Chat Widget - Embeddable chat widget for AI agents
agent-chat binary for windows/amd64
Agent chat backend (Express + Socket.IO + AI SDK)
Agent chat widget library built on the bstp widget starter infrastructure
React component library for Tachyon agent chat, plus agent skill definitions
A Fluent AI package which contains React components for the Fluent Agent chat experience found in the docsite.
AI Agent Chat Component for React with complete style isolation
One-command local audit for credential-like values in coding-agent chat histories.
A salon for agents: real-time channels and API-first agent chat.
Agent chat sessions and clients for Meshagent TypeScript applications.
Agent chat backend (Express + Socket.IO + AI SDK)
Headless React controller for admission agent chat experiences.
Adaptive prompting techniques, K-means task clustering, and temperature optimization for the Brainwires Agent Framework
Speech (TTS / STT) provider clients for the Brainwires Agent Framework — Azure Speech, Cartesia, Deepgram, ElevenLabs, Fish Audio, Google TTS, Murf, plus browser-native `web_speech` (wasm32)
Codebase indexing + hybrid retrieval (vector + BM25) for the Brainwires Agent Framework. Includes AST-aware chunking via tree-sitter (12 languages), Git history search, and reranking via spectral diversity / cross-encoder.
Built-in concrete tools for the Brainwires Agent Framework — bash, file_ops, git, web, search, code_exec, semantic_search, browser, email, calendar, system. Built on `brainwires-tool-runtime`.
Tool execution runtime for the Brainwires Agent Framework — executor trait, registry, error taxonomy, sanitization, validation, transactions, smart router, plus optional orchestrator / OAuth / OpenAPI / sandbox / sessions / RAG-tool-search modules
Nansen blockchain analytics adapter for tail-fin: token analytics, smart money, wallet profiler, Hyperliquid
A simple chat tool for AI agents to communicate with each other via a shared SQLite-backed message queue. Includes CLI and web UI.
Claw is an Agent framework built on ruby-mana. Adds interactive chat, persistent memory with compaction, knowledge base, and runtime state persistence.
A unified platform for knowledge, task management, and chat communication with AI Agents
Writing of agents for monitoring, chatting, ... should be easy. Ragent eases this with a small extraction layer over celluloid.
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.
Route messages to specialized RubyLLM chat agents based on semantic similarity using embeddings and kNN lookup
One beautiful Ruby API for GPT, Claude, Gemini, and more. Easily build chatbots, AI agents, RAG applications, and content generators. Features chat (text, images, audio, PDFs), image generation, embeddings, tools (function calling), structured output, Rails integration, and streaming. Works with OpenAI, Anthropic, Google Gemini, AWS Bedrock, DeepSeek, Mistral, Ollama (local models), OpenRouter, Perplexity, GPUStack, and any OpenAI-compatible API. Minimal dependencies - just Faraday, Zeitwerk, and Marcel.
Plugin engine providing OpenAI-compatible /v1/chat/completions and /v1/models endpoints using Collavre AI agents with context injection.
A Rails engine providing comprehensive observability for LLM-powered applications. Features include session tracking, trace analysis, prompt management, cost monitoring, and optional chat/agent testing UI (with RubyLLM integration).
Wraps RubyLLM::Chat with input/output contracts, business-rule validation, retry with model escalation on validation failure, pre-flight cost ceilings, and an evaluation framework. Sibling abstraction to RubyLLM::Agent — same niche (reusable class-based prompts), wider contract.
The telegram_support_bot gem provides Rails applications with an easy-to-integrate Telegram bot, designed to enhance customer support services. By leveraging this gem, developers can swiftly add a Telegram-based support desk to their application, enabling direct communication between users and support agents through Telegram. Features include automatic message forwarding to a designated secret chat for support agents, the ability to reply directly from the secret chat to users, and customizable responses for common queries. This gem simplifies the process of setting up a robust support channel on one of the most popular messaging platforms, making it an ideal solution for businesses looking to improve their customer service experience.
Framework-agnostic SDK for sending/receiving messages across chat platforms. Supports WhatsApp Cloud API, Telegram Bot API, Facebook Messenger, LINE Messaging API, Slack Web API, and LiveChat Agent API.
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.