Business agents

<div align="center"> <a href="README.md">🇺🇸 English</a> | <a href="README.zh.md">🇨🇳 中文</a> | <a href="README.ja.md">🇯🇵 日本語</a> </div>

Simple caching wrapper for AI SDK tools - cache expensive tool executions with zero configuration

Native CLI binary for @anthropic-ai/claude-agent-sdk on win32-arm64

The official TypeScript library for the Anthropic Foundry API

[nalaso/anthropic-vertex-ai](https://github.com/nalaso/anthropic-vertex-ai) is a community provider that uses Anthropic models through Vertex AI to provide language model support for the Vercel AI SDK.

OpenInference instrumentation for Anthropic

The translation layer for LLM provider messages

Helicone provider for Vercel AI SDK

Browser AI model provider for Vercel AI SDK (Chrome & Edge)

<div align="center"> <a href="https://github.com/goat-sdk/goat">

Security, cost, and health governance proxy for MCP infrastructure — three-layer detection engine (regex + schema + LLM), monorepo, corpus, CI/CD

Tabby终端AI助手插件 - 支持多AI提供商（OpenAI、Anthropic、Minimax、GLM、Ollama、vLLM）和MCP服务器

Cost calculator for Vercel AI SDK token usage. Supports OpenAI, Anthropic, Google, xAI (Grok), and DeepSeek with long context pricing, prompt caching, and reasoning tokens.

MIMI AI Assistant SDK — LLM-powered chat widget for Thai online shop CRM

Node-RED integration with Home Assistant through websocket and REST API

Embedded MQTT broker + MCP server for multi-agent coordination

Tutti runtime — multi-agent orchestration for TypeScript

AI guardrails and orchestration for Directive. Prompt injection, PII detection, cost tracking, multi-agent patterns.

Multi-agent brainstorming through a shared file. Agents join, talk, watch, and mark themselves done.

Universal LLM Command Line Interface with multi-agent support and task management

Multi-Channel Platform for WhatsApp with multi-agent conversation management

Multi-agent workflow runtime with intelligent routing, guardrails, and observability

Production-grade agent framework with structured context management, compaction, tools, and MCP support

Browser extension support for Jarvis Agent framework.

A lightweight agent framework for the Anthropic API

A minimal, extensible TypeScript Agent framework

Programmatic SDK for building AI agents with Robota — provides InteractiveSession, createQuery(), command APIs, permissions, hooks, and context loading

AI Agent Framework for building intelligent agents with LLM integration, function calling, and reflection capabilities

Agent framework integrations for OrmAI — Vercel AI SDK, LangChain, OpenAI, Anthropic, LlamaIndex, Mastra

Open-source RevOps agent framework for HubSpot and Salesforce

Production-grade AI agent framework — the Next.js for AI agents

A simple and powerful Typescript based agent framework to help businesses thrive in the AI Agent revolution.

Multi-threaded, unopinionated, and task-agnostic AI agent framework.

FormAgent SDK - AI Agent framework with streaming support, tool execution, skill management, and hooks system

A lightweight, extensible AI Agent framework with tool calling, MCP integration, and streaming support

Type-safe AI agent framework for Igniter.js with MCP integration, custom toolsets, and memory system

A lightweight, extensible AI Agent framework with tool calling, MCP integration, and streaming support

TypeScript AI Agent framework - from single agent to multi-agent cluster orchestration

🧠 Generic Multi-Provider AI Agent Framework - No SDK dependencies, Raw HTTP only

A modular AI agent framework with multi-LLM support, tool execution, browser/desktop control, Feishu/QQ integration, and self-evolving skills

🌟 The Revolutionary 5-Minute AI Agent Framework for TypeScript/JavaScript - Build production agents 10x faster!

Enterprise-grade AI Agent Framework - DDD Architecture, Microkernel, ReAct Thinking, Multi-LLM Support, MCP Protocol, Secure Sandbox

AI agent framework with defense-in-depth security, multi-agent orchestration, and provider abstraction

Self-hosted Claude AI agent framework — gateway, memory, tools, Telegram, cron, heartbeat. Full system access via tool_use.

The core agent implementation for the Lit AI Agent framework. This package provides the main functionality for processing natural language instructions and executing blockchain operations through registered tools.

Multi-provider AI agent framework for Model Context Protocol (MCP) servers

Browser agent framework powered by Playwright + local Chrome session

Portable agentic workflow orchestration system with strict identity and gate discipline

Anthropic (Claude) adapter for agentic-kit

Non-Agentic Provider for Anthropic in Composio SDK

Agentic AI Library specialized in LLM Function Calling

Agentic AI Library specialized in LLM Function Calling

Shared primitives and common utilities for the Salesforce agentic DX packages

harmony-agentic-decisions. Production-grade human-in-the-loop decision workflows with LLMs and messaging channels.

Agentic AI Library specialized in LLM Function Calling

Agentic AI Library specialized in LLM Function Calling

Secure runtime for AI agents. Policy-enforced tool execution, secret blocking, audit trails. Drop into OpenAI, Anthropic, LangChain, CrewAI. Zero dependencies.

The Parasitic Browser Bridge for CrewAI. Control authenticated Chrome sessions via MCP.

TypeScript SDK for autonomous AI agents — on-chain payments, reputation, marketplace on Base blockchain. Compatible with LangChain, CrewAI, AutoGen, Eliza, Claude MCP.

Agent payment infrastructure MCP server. Give AI agents autonomous payment capability — stablecoin transfers, currency swaps, agent wallets, and fiat operations on Hedera. Works with Claude, LangChain, CrewAI, AutoGPT.

Seracade is a drop-in OpenAI-compatible routing proxy for AI agent teams. Six named capabilities: Call (every request, addressable and replayable), Step (sub-Call routing context inside agent trajectories), Quality Score (calibrated, version-stamped quali

MCP server with 11 read-only tools for exchange fees, referral links, country compliance, Binance TradFi perpetuals, cost calculations, and news.

Drop-in Tessera integration for the Mastra agent framework. One line of config routes every Mastra Agent's LLM calls through Tessera's auto-route + auto-cache + auto-compress + auto-batch proxy. Compatible with @ai-sdk/openai, @ai-sdk/anthropic, @ai-sdk/m

Connect your agent to pre-computed market context that improves reasoning and reduces token usage.

MCP server for AgentForge — trust audit (check_trust, evaluate_policy, list_trusted, recommend) plus action tools (discover, broadcast_search, call_tool, register_agent) so any agent can find and use 100+ MCP servers in one connection.

Monitor any AI agent system. Auto-detects failures, sends alerts, audits OS processes. Zero config, zero dependencies.

A2A (Agent-to-Agent) protocol wrapper for the GitHub Copilot SDK. Drop a JSON config file in, get a fully-spec-compliant A2A server out. Supports any agent persona, MCP tool servers, streaming, context building, and multi-turn conversations.

Persistent memory SDK for AI agents — Stanford Generative Agents architecture on Supabase + pgvector

Three hooks that wire an AI copilot into your React app's state, actions, and forms. AI SDK 6 native. Ships with an optional .pilot/ skills folder and an `agentickit` CLI for scaffolding it. MIT.

A framework-agnostic, git-native standard for defining AI agents

Framework-agnostic agent action logger with optional AgentLair backend

The email inbox API for AI agents. Send, receive, reply, and manage threaded email conversations programmatically.

Direct LLM API bridge for Tunnlo (Anthropic, OpenAI, Ollama)

AI governance SDK — intercept, audit, and control AI agent tool calls. Add human-in-the-loop approval, kill switches, and a full audit trail to any AI agent.

Security scanner and trust layer for AI agent skills/plugins — scan URLs, files, and directories for credential exfiltration, injection, and other threats

Agoragentic is a marketplace where AI agents buy and sell task execution, paid in USDC, with a public receipt for every call. Official Node.js SDK and agora CLI for Triptych OS (Agent OS) deployed agents and swarms, Router / Marketplace routing, receipts,

Interven AI Agent Firewall — drop-in gateway proxy. Scan every tool call through policy + risk scoring. One command, zero infrastructure.

Framework adapters for connecting TypeScript agents to the Agent2Agent protocol.

Non-custodial spending controls for AI agent wallets. Enforce limits without holding keys.

Interven JS/TS SDK — Approvals + Audit for AI Agents. Scan tool calls through policy + risk scoring. Block, redact PII, or route to human approval via Slack.

Runtime protection and security monitoring for AI agents — The CrowdStrike for AI Agents

Safety controls for AI agents — budgets, approvals, rate limits, audit logs, and DLP

Cognitive Memory OS for AI Agents — persistent, self-improving, multi-agent memory

Framework-agnostic agent action logger. Logs locally by default. Connect to AgentLair for persistent, queryable audit trails.

The API layer for AI agents. Dashboard + 22K APIs + 18 Direct Call providers. MCP native.

The simplest way to add USD payments between AI agents. Powered by Stripe.

Security and identity infrastructure for AI agents

Register your AI agent on Pinchr in one command

AG-UI adapter for the Angular AI agent UI — connect any AG-UI-compatible backend to the same chat surface.

A package which exports API route passthrough functions for using LangGraph from the client with Next.js

LangGraph BaseCheckpointSaver backed by agentsmcp (AgentMailbox). Drop-in checkpointer for LangGraph.js — your graph state lives in an AgentMailbox thread.

Jarela — local chat interface for LangGraph agents (multi-provider, single-process, SQLite-backed).

Composable lightweight smart agent core (no LangGraph) with pluggable model adapters.

AI Agent Observability — Track OpenAI, LangChain, LangGraph, Bedrock, Vercel AI, Anthropic

Open-source CopilotKit + LangGraph chat history persistence. Restore thread history on page refresh.

LangGraphJS checkpoint saver implementation for Supabase with UUID thread_id and Supabase Storage support

Tamper-evident audit log for AI agent memory operations. Adapters for Anthropic Memory, Letta, Mastra, Mem0, LangChain, LangGraph, GBrain, and Hermes Agent (via psy-core-hermes).

MCP Workflow Engine - A framework for building deterministic workflows with LangGraph and Model Context Protocol

Open-source CopilotKit + LangGraph chat history persistence. Restore thread history on page refresh.

High-performance execution tracing for Node.js with LangChain/LangGraph/OpenAI/Vercel AI auto-instrumentation