Microsoft has introduced a preview of the Microsoft Agent Framework, an open-source improvement equipment for .NET and Python for creating AI brokers and multi-agent workflows.
It helps creating particular person brokers in addition to graph-based workflows to attach up a number of brokers.
In accordance with Microsoft, the Agent Framework is a direct successor to its different initiatives Semantic Kernel and AutoGen, using foundations from each. It brings collectively Semantic Kernel’s enterprise-grade options like thread-based state administration, sort security, filters, telemetry, and mannequin and embedding help, with AutoGen’s abstractions for single- and multi-agent patterns.
“Each had passionate customers — however every had gaps,” Microsoft wrote in a weblog put up. “Builders requested us: why can’t we now have each — the innovation of AutoGen and the belief and stability of Semantic Kernel — in a single unified framework?”
Like Semantic Kernel and AutoGen, the Agent Framework may also be open-source and Microsoft welcomes the group to contribute.
The Agent Framework was constructed round open requirements, and helps MCP, Agent-to-Agent (A2A), and OpenAPI. MCP permits brokers to find and use exterior instruments or knowledge sources, A2A permits builders to construct brokers that may collaborate with different brokers, and OpenAPI help permits any REST API that follows the OpenAPI specs to be imported as a callable software. Brokers can run in containers, on-premises, or throughout a number of clouds.
It helps a number of completely different orchestration patterns, together with sequential orchestration for step-by-step workflows, concurrent orchestration, group chat orchestration for brokers to collaborate, handoff orchestration to maneuver obligations between brokers, and magnetic orchestration, which permits supervisor brokers to construct a process ledger that coordinates specialised brokers and people to resolve complicated issues.
Different options that the Agent Framework has contains built-in connectors to enterprise methods, pluggable reminiscence modules, YAML and JSON definitions for declarative prompting, help for OpenTelemetry, and the power for brokers to pause, resume, and recuperate from interruptions.
“Brokers are quick turning into the subsequent layer of utility logic — reasoning about targets, calling instruments, collaborating with one another, and adapting dynamically. With Microsoft Agent Framework, builders now have a single, open-source basis that carries one of the best of analysis innovation into manufacturing with the sturdiness, observability, and enterprise readiness required to scale,” Microsoft wrote.
