Microsoft Agent Framework
Microsoft Agent Framework is an open source SDK and runtime designed to help developers build, orchestrate, and deploy AI agents and multi-agent workflows using languages such as .NET and Python. It combines the simple agent abstractions of AutoGen with the enterprise-grade capabilities of Semantic Kernel, including session-based state management, type safety, middleware, telemetry, and broad model and embedding support, creating a unified platform for both experimentation and production use. It introduces graph-based workflows that give developers explicit control over how multiple agents interact, execute tasks, and coordinate complex processes, enabling structured orchestration across sequential, concurrent, or branching scenarios. It supports long-running and human-in-the-loop workflows through robust state management, allowing agents to maintain context, reason through multi-step problems, and operate continuously over time.
Learn more about Microsoft Agent Framework
Akka
Akka is a production-grade runtime and agentic AI platform built to make complex distributed systems reliable, resilient, and governable. The platform supports operational data processing, streaming, real-time analytics, long-running workflows, durable memory, edge coordination, digital twins, model inference, and agent execution. Akka combines actor-based concurrency, clustering, durable in-memory state, event sourcing, streaming, backpressure, and active-active high availability to support mission-critical workloads. Its Agentic AI Platform helps teams specify, generate, test, run, govern, and verify AI systems with agents, tools, orchestrations, integrations, memory, APIs, streaming, guardrails, evaluations, HITL workflows, and audit logging. Akka is designed to provide uniform governance, predictable pricing, cloud freedom, and reliability SLAs for enterprise AI and distributed applications.
Learn more about Akka
Claude Agent SDK
The Claude Agent SDK is a developer toolkit that enables the creation of autonomous AI agents powered by Claude, allowing them to perform real-world tasks beyond simple text generation by interacting directly with files, systems, and tools. It provides the same underlying infrastructure used by Claude Code, including an agent loop, context management, and built-in tool execution, and is available for use in Python and TypeScript. With this SDK, developers can build agents that read and write files, execute shell commands, search the web, edit code, and automate complex workflows without needing to implement these capabilities from scratch. It maintains persistent context and state across interactions, enabling agents to operate continuously, reason through multi-step problems, take actions, verify results, and iterate until tasks are completed.
Learn more about Claude Agent SDK
AAES Govern
AAES Govern is pre-launch, self-hosted software for enterprise AI agent requests routed through configured credential paths. It checks permissions, required human approvals and spending limits, reserves evaluated amounts before authorization, and records signed decisions for offline integrity checks. An agent's direct credentials or alternate route can bypass enforcement; observation-only integrations cannot block activity. Customer-run evaluation is available through a paid USD 40,000 three-month design partnership covering AAES Govern and the separate AAES Operate product; production rates are unpublished. Managed Govern hosting is planned, not offered. The separately released Apache-2.0 aaesverify CLI checks exported-record integrity against a separately trusted public key; it cannot establish complete capture, input truth, or downstream execution. AAES has no production customer results or independent certification.
Learn more about AAES Govern