agent-framework and agentica
These are competitors: both are general-purpose Python frameworks for building AI agents with tool-calling capabilities, but microsoft/agent-framework is a mature, heavily-adopted enterprise solution while agentica is a lightweight async-first alternative for simpler use cases.
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 agentica
shibing624/agentica
Agentica: Lightweight async-first Python framework for AI agents. 轻量级异步优先的AI Agent框架，支持工具调用、RAG、多智能体和MCP。
Provides 40+ built-in tools (search, code execution, file operations, OCR, image generation) and supports multiple agent patterns including Teams for dynamic delegation and Workflows for deterministic orchestration. Built on async-first primitives enabling parallel tool execution via `asyncio.gather()`, with integrations for LangChain/LlamaIndex RAG, MCP protocol support across stdio/SSE/HTTP transports, and a Markdown-based Skill system for model-agnostic capability injection.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work