Terminal animation effects for agents' thinking state — WASM/JS bindings
Terminal animation effects for agents' thinking state — WASM/JS bindings
A home for your AI agents
Maps proxy protocols to `http.Agent` implementations
The **[Moonshot AI provider](https://ai-sdk.dev/providers/ai-sdk-providers/moonshotai)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the [Moonshot AI](https://platform.moonshot.cn) platform, including the Kimi model serie
The **[Alibaba provider](https://ai-sdk.dev/providers/ai-sdk-providers/alibaba)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model, embedding model, and video model support for [Alibaba Cloud Model Studio](https://modelstudio.console.alib
MCP server for sequential thinking and problem solving
Client side APIs for working with Salesforce agents
SOTA NPM module for agentic processes using local or cloud LLMs.
Turn a function into an `http.Agent` instance
Breakthrough Method of Agile AI-driven Development
Paperclip adapter for Hermes Agent — run Hermes as a managed employee in a Paperclip company
A pi extension extension that brings smart Claude Code-style autonomous sub-agents to pi.
Headless CLI client for the Agent Client Protocol (ACP) — talk to coding agents from the command line
No description provided.
Playwright Tools for MCP
MCP server for Chrome DevTools
provides utilities to route requests through a configurable proxy
tar for node
Comlink makes WebWorkers enjoyable
LangGraph
Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action
A agent component for Convex.
The OpenAI Agents SDK is a lightweight yet powerful framework for building multi-agent workflows.
Modern service orchestration framework designed for the AI era. Enables rapid development of both traditional and AI-powered applications through composable, testable operations. Features agent-oriented architecture, AI-friendly patterns, and robust service composition.
Generates novel ideas via divergent, convergent, and combinational creativity modes; tracks creative potential via EMA; incubates and evaluates ideas using Guilford quality factors
RubyPi is a minimal, composable AI agent harness for Ruby. Build production-ready LLM agents and AI agents with a unified provider interface across OpenAI, Anthropic Claude, and Google Gemini, plus first-class support for tool calling (function calling), streaming responses, automatic retries, provider fallback, context compaction, and a think-act-observe agent loop. Anti-framework design — small, idiomatic, and explicit. Ideal for building autonomous AI agents, ReAct agents, tool-using LLM agents, and chatbots in Ruby.
A small collection of base classes used for interacting with remote machines over ssh. With them, you can use AMQP (via Symphony) to run batch commands, execute templates as scripts, and perform any batch/remoting stuff you can think of without the need of separate client agents.
CodeAct provides Think-Code-Observe agents that synthesize and execute Ruby code dynamically. Ship DSPy.rb workflows that write custom Ruby code while tracking execution history, observations, and safety signals.