agent-framework and agentic-fleet
The second is a specialized reasoning layer built on top of the first, making them complements rather than competitors—Agentic Fleet extends Microsoft Agent Framework's capabilities with adaptive multi-agent coordination patterns.
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 agentic-fleet
Qredence/agentic-fleet
Adaptive Agentic AI Reasoning using Microsoft Agent Framework -- Join the Discord for suggestion or support ! https://discord.gg/ebgy7gtZHK
# Technical Summary Implements a self-optimizing five-phase pipeline (analysis → routing → execution → progress → quality) that automatically routes tasks to specialized agents, leveraging DSPy for offline-compiled structured reasoning and the Microsoft Agent Framework for reliable distributed execution. Integrates with OpenAI APIs, Tavily search, browser automation, and Model Context Protocol (MCP) tools through a unified ToolRegistry adapter pattern. Provides both FastAPI backend with streaming SSE/WebSocket events and React 19 frontend, with observability via OpenTelemetry and Langfuse, and persistence options including Azure Cosmos DB.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work