agent-framework and miiflow-agent
These are complements: Microsoft's framework provides the orchestration infrastructure for multi-agent workflows while MiiFlow offers a lightweight LLM abstraction layer that could be integrated as a provider within that orchestration to handle diverse model backends.
About agent-framework
microsoft/agent-framework
A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.
Supports graph-based workflows with streaming, checkpointing, and human-in-the-loop capabilities for deterministic function composition. Built-in OpenTelemetry observability, middleware system for request/response processing, and a DevUI for interactive agent development and debugging. Works with multiple LLM providers and includes experimental labs for benchmarking and reinforcement learning research.
About miiflow-agent
MiiFlow/miiflow-agent
Lightweight Python SDK for LLMs with unified API across 9 providers. Built-in ReAct & Plan-Execute agents, streaming, native tool calling, context injection, structured outputs, and observability.
Provides composable agentic patterns (ReAct and Plan & Execute) with minimal dependencies (~8 core packages) compared to LangChain's 50+, plus automatic tool schema generation and context injection via dependency injection patterns similar to Pydantic AI. Streaming is event-based rather than token-callback focused, and the codebase stays ~15K lines for focused production use without fighting abstraction layers.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work