SuperAPI AI Directory
Partner with us中文AI newsFavorites

AI agents

3,022 results · Page 17 of 84

Phidata

AI agents

Phidata (now named Agno) is a self-driving agent platform that runs in the user's own cloud environment. It provides three major components: the Agno SDK, the AgentOS runtime, and the Agno control plane, and supports building agents, teams, and multi-agent workflows with code, no-code, or natural language. The platform comes with more than 100 built-in toolkits, natively supports more than 30 model providers, and is compatible with frameworks such as LangGraph, DSPy, and Claude SDK. Users can build agents for customer-facing customer service, sales, research, finance, weekly reports, and more, and deploy agents to their own products, ChatGPT, Claude, Slack, Discord, and other channels via REST, MCP, or APIs. AgentOS provides durable execution, distributed state, request isolation, resumable streaming, JWT-based RBAC, audit logs, and observability; the control plane can manage all runs, traces, sessions, evaluations, and usage metrics in real time, and supports roles and permissions, approvals, and guardrails. The platform emphasizes that data stays in your own database, can run in any container-capable cloud, on-premises, or hybrid environment, is priced at a flat rate, does not store data or run compute, and therefore has no storage fees, retention fees, or per-trace billing. Official information shows it has 41K GitHub stars, Fortune 5 customers, and is SOC 2 compliant.

Read more

Prefect

AI agents

Prefect is a platform for orchestrating data, machine learning, and AI agent workflows, with its core based on the open-source Prefect framework. Developers only need to add the @flow decorator to a Python function to gain state tracking, logging, and automatic retries. It can replace fragile cron jobs, support automatic retries on failure, on-demand scaling, and task tracking, and provide a unified interface to view run status across teams and infrastructure. Prefect also provides the open-source FastMCP framework and FastMCP Gateway for building MCP servers to connect AI agents to various tools and data. It supports managed compute, your own VPC, or a hybrid deployment of both, and the company says the enterprise edition provides a 30-minute response SLA.

Read more