Posts about maf. ← All posts
The first ten posts treated MAF as having four orchestration patterns. The official docs say five. Here are the two I missed — Group Chat and Magentic — with the API surface, when to pick each, and the test path that catches them at build time.
I built memory, communication, security, governance, and evals from scratch first. Then I deleted most of it and used the official MAF packages. Here
PROVIDER=ollama, granite4.1:3b, zero API keys, no Azure account. How to make a multi-agent project that demonstrates enterprise patterns run end-to-end on a laptop in 90 seconds.
Single-turn evals check one decision. Multi-turn evals check the whole trajectory. Here
OWASP Agentic Top 10 coverage with YAML policy files, two API surfaces (one-line wrapper and programmatic evaluator), and a metric bridge that shows policy denials in Grafana.
OpenTelemetry through MAF
The reference architecture distinguishes request-based and message-driven agent communication. For in-process orchestration, MAF
AgentSession is short-term memory. MemoryContextProvider + MemoryFileStore is long-term memory. Mem0 is long-term memory when you want it hosted. Here
The Microsoft Agent Framework deliberately does not ship an agent registry. Here
Sequential, Concurrent, Handoff, and Custom WorkflowBuilder. Four shapes the Microsoft Agent Framework ships out of the box. Each one is the right answer to a different question.
Microsoft published a 12-chapter reference architecture for multi-agent systems and a separate framework (MAF) to build them. I implemented one on top of the other and learned what each chapter actually demands in code.