Microsoft Agent Framework

Active
GitHub Python MIT

Description

Microsoft's comprehensive multi-language framework for building, orchestrating, and deploying AI agents and multi-agent workflows with support for Python and .NET.

Key Features

  • Multi-language support — first-class Python and C#/.NET with consistent APIs
  • Graph-based orchestration patterns: sequential, concurrent, handoff, and group collaboration
  • OpenTelemetry built-in for distributed tracing, monitoring, and debugging
  • Declarative agent definitions via YAML for faster setup and version control
  • Agent Skills — build domain-specific knowledge bases from files, code, and libraries
  • Foundry Hosted Agents — deploy to cloud infrastructure with just 2 lines of code

Use Cases

💡 Enterprise-grade multi-agent workflows with durability, restartability, and governance
💡 Cross-platform agent development for teams using both Python and .NET stacks
💡 Production deployment of agents with human-in-the-loop control and checkpointing
💡 Migrating from Semantic Kernel or AutoGen to a unified agent framework
💡 Rapid prototyping with DevUI interactive debugger and declarative agent configs

Strengths & Limitations

Strengths

  • Actively maintained, recent updates
  • High community interest (13.3k stars)
  • Permissive open-source license (MIT)

Quick Start

pip install agent-framework && python -c "import asyncio; from agent_framework import Agent; from agent_framework.foundry import FoundryChatClient; from azure.identity import AzureCliCredential; async def main(): agent = Agent(client=FoundryChatClient(credential=AzureCliCredential()), name='Agent', instructions='You are helpful.'); print(await agent.run('Say hello')); asyncio.run(main())"

Related Projects

Hive

11.0k · Python
Active B

Hive is a production-ready multi-agent execution harness providing state management, failure recovery, observability, and human-in-the-loop control with auto-generated multi-agent topologies for complex business workflows.

multi-agentagent-frameworkproduction +3
  • · Zero-setup, model-agnostic execution harness that auto-generates multi-agent topologies for complex workflows
  • · Graph-based execution DAG for safe parallel task coordination with deterministic fault tolerance
  • · Persistent role-based memory that evolves with project context — no manual state management

Ouroboros

5.8k · Python
Active A

Ouroboros is a spec-driven multi-agent framework that shifts from traditional prompting to specification-driven development, supporting multi-agent collaboration, MCP tool integration, and automated workflow orchestration for building high-quality agent systems.

multi-agentframeworkagent +4
  • · Spec-first workflow: Socratic interview → immutable seed spec → execution → evaluation
  • · Multi-runtime adapter supporting Claude Code, Codex CLI, OpenCode, Hermes, Gemini, Kiro, Copilot
  • · Three-layer architecture: Kernel (contract engine), Plugins (domain workflows), Shell (TUI cockpit)

AgentScope

30.5k · Python
Active A+

Open-source multi-agent framework from Alibaba, enabling the construction of observable and interpretable agents with rich distributed capabilities.

agent-frameworkmulti-agentdistributed +2
  • · Built-in ReAct Agent — Create agents with reasoning and tool-use capabilities in 5 minutes
  • · Tool & Skill System — Built-in Bash, Grep, file I/O tools with custom extension support
  • · Multi-Agent Orchestration — Flexible multi-agent collaboration via Message Hub

Spring AI Alibaba

10.8k · Java
Active A

Spring AI Alibaba is an Agentic AI Framework for Java developers, built on the Spring ecosystem to provide multi-agent collaboration, workflow orchestration, and RAG capabilities.

javaspringmulti-agent +4
  • · Multi-agent orchestration with SequentialAgent, ParallelAgent, RoutingAgent, and LoopAgent patterns
  • · Graph-based workflow runtime for conditional routing, nested graphs, and state management
  • · Context Engineering built-in with human-in-the-loop, context compaction, and dynamic tool selection

Related Articles