Category
Business agents
4,517 Business AI agents indexed on MeshKore — the most complete public catalog, ranked by popularity and updated daily.
4,517 agents · ranked by popularity · refine in the directory →
Business agents — page 44 of 46
Own your LLM's web search: a local search -> fetch -> rank pipeline that replaces hosted web_search tools at a fraction of the cost
Phronesis review: compare features, pricing, use cases, access model, and alternatives for this Model Context Protocol (MCP) agent in 2026. A neutral decision-assurance layer for autonomous agent actions.
ApparelHub MCP server: workflow-level tools that let an AI agent design apparel, build products, and sync them to sales channels through the ApparelHub platform.
Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.
Loopback bidirectional Anthropic/OpenAI API proxy with tool-call validation and multi-provider routing.
Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.
Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.
Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.
Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.
Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.
Next-Generation Non-Custodial M-of-N MPC Security & x402 USDC Payment Infrastructure for Autonomous AI Agents
This package contains the LangChain.js integrations for Anthropic via the anthropic-ai/sdk package.
NexusGenesis Agent Autonomous Key Security — PQC (Dilithium2) keys, AES-256-GCM encryption, three-tier key derivation, and human takeover. Private keys never leave the agent/browser.
Klyrune — agentic terminal assistant with multi-provider support (OpenAI, Anthropic, DeepSeek, 9Router, custom endpoints), tools, sessions, memory, todos and plan/build modes.
TypeScript agent orchestration entrance (createAgent, createTeam) — durable memory/HITL/stream replay when you need them. Production-oriented architecture, young ecosystem — not a graph DSL.
Noir model — optional bounded single-shot LLM layer (anthropic / openai / openai-compatible); agent loops are impossible by design.
OpenAI Agents SDK-backed AgentHarness implementation for @salesforce/sfdx-agent-sdk
A lightweight terminal chat agent built on the OpenAI Responses API through the official @eliware/openai client.
TypeScript runner for Sovara — wrap a script in a single function to record every LLM call, tool invocation, and log line into a structured run graph.
Provider adapters for AgentsKit.
Offline BPE tokenizer for OpenAI, Anthropic, and Gemini — zero dependencies
Open-source CRM control plane and safety toolbox for AI agents: deterministic audits, reviewable patch plans, approval-gated write-back, conflict detection, and entity resolution for HubSpot and Salesforce.
Outlook Assistant — MCP server with 22 tools for email, calendar, contacts, and settings via Microsoft Graph API
<div align="center"> <h1>Nx Plugin for AWS</h1> <h3>Build full-stack AWS apps in minutes</h3> <a href="https://opensource.org/licenses/Apache-2.0"> <img src="https://img.shields.io/badge/License-Apache%202.0-yellowgreen.svg" alt="Apa
Umbrella package for the Agent Framework (TypeScript): one install for the core, the OpenAI / Anthropic / Foundry providers, MCP, A2A and hosting, each re-exported under a subpath.
Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.
Type-safe LLM-powered functions. Write intelligent functions with decorators, not agents.
A deterministic Python library for parsing, normalizing, and validating brokerage statements across brokers and statement formats.
Local multi-client RAG server over the Model Context Protocol
LiteLLM proxy logging callback that appends request telemetry to DuckLake tables through an Arrow Flight SQL endpoint
Resilient Multi-Provider LLM Fallback Router (DeepSeek, OpenAI, Ollama, Anthropic).
Local collector for LLM token usage emitted through OpenTelemetry
Zero-dependency, stdlib-only Python client for rusty-server (threads, runs, SSE streaming, time travel, assistants, crons, KV store, durable tasks)
A modular, extensible AI Agent framework with multi-provider support and plugin architecture
Synchronous and asynchronous WebSocket client transport for Swarmauri.
Offline-LLM natural-language control layer for the sweep stack. Routes user intent (chat / files) through a local LLM (vLLM/Ollama/llama.cpp) into validated sweep-tasks specs and executes them.
Minimal tool-loop harness for LLM agents. Keep your provider SDK, keep your messages, add a correct tool loop.
A firewall for AI agent spending. 9 composable rules evaluated per-transaction in <1ms. Pure Python stdlib — zero dependencies.
A dairy-free RAG pipeline for delicious semantic similarity, clustering and NER.
Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.
Tool de LangChain para consultar LEX-MEX (leyes federales mexicanas con IA).
Endpoint-based evaluation harness for legal RAG systems
Provider-neutral synchronous chat adapters for OpenAI, Claude, DeepSeek, OpenRouter, and LiteLLM.
A grounding-first RAG library: threshold-gated retrieval, concern-based chunking, a locked grounding prompt, and built-in faithfulness evaluation as the default path, not an optional rail.
LlamaIndex 기반 RAG All-In-One 라이브러리
Framework-agnostic AI/LangChain engine: OpenAI/Anthropic/Bedrock chat models, Pydantic structured outputs, tool-calling agents, and pure cost calculators.
GenieAI review: compare features, pricing, use cases, access model, and alternatives for this Legal agent in 2026. Rated 5/5 from 1 verified review. Agree With Confidence
BYOK AI agent CLI - Terminal'den AI ile kod yazın
The official ToolPlex client for AI agent tool discovery and execution
Passive-awareness swarm bus for agent harness pods — threads, non-blocking mentions, and background watchers that fold teammate discoveries in at step boundaries (AgentRadio, arXiv:2607.28430). Freeze the model, evolve the comms policy.
DeepSeek-backed search provider (native web_search via the Anthropic-compatible API) for the DeepSeek Harness web capability seam (ctx.web)
n8n community nodes: Standalone AI Agent with multi-provider LLM support and integrated Langfuse/Phoenix/Helicone observability
@ai-sdk/anthropic with all dependencies updated to latest
Model Context Protocol (MCP) server for Stellar Cyber security operations with specialized multi-agent analysis capabilities
Stealthy and efficient agentic browser driver for AI agents. Few tools, full control, real stealth, max token efficiency.
The embedded catentio agent surfaces for the Forjio family: the agentic CRUD sheet (Agentic + Manual tabs), the docked chat composer, and the adapter seams that let each product route transport through its own BFF.
One tool adapter for the TathaAstu API, with bindings for every major agent framework
Cross-platform decision evidence and reconstruction for regulated AI agents
AgentGov FastAPI gateway (vaults ANTHROPIC_API_KEY; enforces from signed policy cache; §12.1)
Shared AgentPlane control plane: Chronicle envelopes + TokenOps governance over HTTP.
Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.
LLM infrastructure layer with multi-provider fallback, health monitoring, speed probing, and alerting.
A DynamoDB-backed BaseStore for LangGraph — cross-thread memory for agents, no Postgres/pgvector required
Trace LLM calls with a decorator — non-blocking, fail-silent observability SDK.
A Mixture-of-Models OpenAI/Anthropic-compatible LLM gateway that fans out to a panel of models and synthesizes one answer.
Phase-Shifted Agentic Swarm (PSAS) methodology for multi-agent cognitive synchronization
The Agentic Flower Fund review: compare features, pricing, use cases, access model, and alternatives for this Other agent in 2026. Autonomous AI agents for micro-philanthropy funding habitat restoration.
<div align="center" style="margin-bottom: 10px"> <a href="https://www.npmjs.com/package/planby"> <img src="https://i.postimg.cc/J0XMPHNQ/planby-logo.png" alt="Planby logo" /> </a> </div>
🚀 Zero-cost multi-provider AI agent framework. Support for OpenAI, Claude, Ollama + smart routing, cost tracking & RAG.
Deterministic schema validation gates and circuit breakers for LLM function calling
A local-first personal assistant: pluggable model providers, three-layer memory, tracing and evals.
Local LiteLLM proxy for GitHub Copilot models with OpenAI and Anthropic-compatible APIs.
CLI for Tages AI agent memory
MCP server for persistent AI agent memory
Open detection standard -- like Sigma, but for AI agents. Executable rules for prompt injection, tool poisoning, context exfiltration, and MCP attacks. Shipped in Cisco AI Defense. MIT-licensed.
Fireworks AI provider extension for pi - Access Kimi, MiniMax, GLM, DeepSeek, and GPT-OSS models through the Fireworks AI API
Ship agent traces from OpenAI Agents, Claude Agent SDK, LangChain, LangGraph, Vercel AI SDK, n8n and any OpenTelemetry-instrumented agent into Cognipeer Console.
Differential testing of budget enforcement semantics across AI agent frameworks
Pointer to the pypi package `agentic-graphrag`
Agentic GraphRAG: graph-based retrieval-augmented generation with agentic reasoning.
Runtime governance for AI agents. Conduct Guard as a LiteLLM guardrail — enforce runtime policy on every LLM call routed through LiteLLM.
Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.
Proxy Gemini (Vertex AI) completions wrapped in OpenTelemetry trace spans; returns the answer plus the trace/span id.
Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.
Portable Ink distribution of the Claude Agent SDK Python source
Corso online in italiano per non tecnici: 10 puntate su token, modelli, RAG e agenti AI. Prima puntata gratis. Prezzo 9,90 €.
Claude Agent SDK runtime adapter for VAT agents
Gate every LangChain agent action through Qerexa runtime trust enforcement.
Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.
Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.
Lightweight SDK for routing AI agent LLM traffic through a guardrails proxy
LangChain integration for Leanroute. Drop-in `ChatLeanroute` chat model — same interface as `ChatOpenAI`, but routes across 13 LLM providers (OpenAI, Anthropic, Google, DeepSeek, Groq, xAI, and more) with cost caps, failover, and MCP support baked in.
Provider connections for the Axon agent runtime — Anthropic, OpenAI, Google, Groq, Ollama and more.
TypeScript SDK for Verlon AI — the managed AI infrastructure platform that routes requests across LLM providers, evaluates response quality, runs experiments against live traffic, and auto-tunes routing configurations. Agent integration protocol: https://
Stratus Agent CLI: setup walkthrough, agent creation, local runs, and dashboard
The SDK an autonomous agent trades Brier through: quotes, impact-bounded sizing, buy/sell/redeem, identity, evidence, and attested 0G Compute inference.
WhatsApp MCP Server: Human-in-the-loop for AI agents via WhatsApp for confirmations, notifications, and interactive questions.
A multi-agent runtime for Node.js: agents, models, tools, skills, memory and an append-only trajectory.
n8n community node for NabuGate AI gateway & multi-agent flows
A Zod-like schema validation and repair library for Agentic frameworks