MCP Server for DeepSeek API integration - enables Claude Code to use DeepSeek Chat and Reasoner models
OpenAI function/tool definitions for SmartyTalent API
Safe, function-calling AI agents for the browser
A universal LLM client with transparent provider failover, streaming tool execution, pluggable reasoning, and native observability.
Browser-safe, ready-to-register FunctionDefinition tools for Forgewisp agents
Automatic MCP Server & OpenAI Tools Bridge for apcore
Production-ready MCP server for NVIDIA NIM models - 50+ LLMs, multimodal, image generation, embeddings, reranking with rich metadata for agent selection
A lightweight registry for validated AI tools. Build tools with Zod schemas and metadata, register them in a toolbox, and execute/query them with event hooks.
AI-first workflow manager for heavy MCP tools with lazy Agent Skills and patchable runs.
Tool-using planning agent over MCP servers, built on the Vercel AI SDK.
Opinionated, framework-agnostic prompting kit and client-side guards for Planetary Minds agents. Built on top of @planetary-minds/typescript-sdk.
用于开发 AI 应用,适配任意前端框架,支持所有 OpenAI-compatible 大模型,提供对话界面、Agent、MCP、工作流等
Simplr's fraud/identity/phone checks as ready-to-use tools for AI agents — Vercel AI SDK, OpenAI function-calling, and LangChain.
TypeScript SDK for production AI agents — 110+ built-in tools across 14 categories, multi-provider support (OpenAI, Anthropic, Gemini, Ollama), workflow engine, and mode system
Framework-free agentic loop, tool abstraction, MCP client and multi-provider (OpenAI/Anthropic/local) model adapters.
Model Context Protocol (MCP) client support for Forgewisp agents — expose an MCP server's tools as agent FunctionDefinitions
A tiny, zero-dependency, provider-agnostic agent tool-loop for TypeScript. Build your own AI agent in ~100 lines.
Drop-in OpenAI-compatible tool calling for LLMs that don't support function calling natively. Injects tools via prompt, parses tool calls from text, and runs a full agentic loop — with streaming support.
On-device AI for Expo — run Gemma 4, Apple Foundation Models & ML Kit locally: streaming, structured output, tool calling, zero API keys
Local OpenAI Codex Responses API gateway for DeepSeek Chat Completions.
Direct @anthropic-ai/sdk adapter for llm-ports. Implements LLMPort with prompt caching, vision, and tool use support for Claude models.
LLM function-calling adapter for noy-db — expose ACL-scoped collections as tool definitions, then dispatch tool calls back to the vault. Format-agnostic (OpenAI, Anthropic, Vercel AI SDK).
AIPlug Enterprise AI Agent SDK - React & JavaScript