Comparisons / Agno vs CrewAI

Agno vs CrewAI: Which Agent Framework to Use?

Agno agno (formerly phidata) is a lightweight python framework for building agents. CrewAI crewai organizes work into agents, tasks, and crews. Here is how they compare — and what the same patterns look like in plain Python.

By the numbers

Agno

GitHub Stars

39.2k

Forks

5.2k

Language

Python

License

Apache-2.0

Created

2022-05-04

Created by

Agno (formerly Phidata)

github.com/agno-agi/agno

CrewAI

GitHub Stars

48.0k

Forks

6.5k

Language

Python

License

MIT

Created

2023-10-27

Created by

João Moura

github.com/crewAIInc/crewAI

GitHub stats as of April 2026. Stars indicate community interest, not necessarily quality or fit for your use case.

ConceptAgnoCrewAIPlain Python
AgentAgent(model=OpenAIChat(), instructions=[...]) class with run() methodAgent(role, goal, backstory, tools, llm)A function that POSTs to /chat/completions and returns the response
ToolsFunction tools via @tool decorator or built-in toolkits (web search, SQL, etc.)Tool registration with @tool decorator, custom Tool classesA dict of callables: tools = {"search": search_web, "sql": run_query}
Agent LoopAgent.run() handles tool dispatch internally, configurable via show_tool_callsInternal to Agent execution, hidden from userA while loop: call LLM, check for tool_calls, execute, repeat
Memory / KnowledgeKnowledge bases (PDF, URL, vector DB) injected via knowledge param + built-in memoryA list of relevant chunks injected into the system prompt via a retrieval function
Multi-Agent (Teams)Team class with agents list, mode (sequential, parallel, coordinate), and shared memoryA function that calls agent functions in sequence or parallel, passing results between them
StorageSqlAgentStorage, PostgresAgentStorage for persisting sessions and statejson.dump() / json.load() to a file, or a simple DB insert
Task DelegationCrew(agents, tasks, process=sequential/hierarchical)A task queue processed in a while loop with a budget cap
MemoryShortTermMemory, LongTermMemory, EntityMemoryA dict injected into the system prompt
StateTask output passed between agents via Crew orchestrationA dict tracking tool calls and results

What both do in plain Python

Every concept in the table above — agent, tools, loop, memory, state — maps to a handful of Python primitives: a function, a dict, a list, and a while loop. Both Agno and CrewAI wrap these primitives in their own class hierarchies and APIs. The underlying pattern is the same ~60 lines of code. The difference is how much ceremony each framework adds on top.

When to use Agno

Agno adds value when you want a batteries-included agent with minimal boilerplate — especially for multi-modal agents or team orchestration. But each of its abstractions maps to a small piece of plain Python. If your agent is straightforward, writing it directly gives you full control with zero framework overhead.

What Agno does

Agno gives you a single Agent class that wires together an LLM, tools, instructions, knowledge bases, and storage. You configure an agent declaratively — pass in a model, a list of tools, and optional knowledge sources — and call agent.run(). It handles the tool-calling loop, injects knowledge into context, and persists conversation state. Agno also supports multi-modal agents (vision, audio) and team-based orchestration where multiple agents coordinate on tasks. The framework ships with built-in toolkits for common tasks: web search, SQL queries, file operations. Compared to LangChain, it's lighter — fewer abstractions, less indirection. The tradeoff is a smaller ecosystem and fewer third-party integrations.

The plain Python equivalent

Every Agno abstraction maps to plain Python. The Agent class is a function that POSTs to the LLM API, checks for tool_calls, dispatches them from a dict, and loops. Knowledge bases are a retrieval function that fetches relevant chunks and injects them into the system prompt. Memory is a messages list. Storage is json.dump(). Teams are a function that calls multiple agent functions and combines their outputs. The entire agent — with tools, knowledge retrieval, memory, and multi-agent coordination — fits in about 60 lines. No base classes, no decorators. When something breaks, you debug your function, not a framework's internals.

Full Agno comparison →

When to use CrewAI

CrewAI shines for multi-agent setups where you want named roles ("researcher", "writer"). But the core mechanics — tool dispatch, the agent loop, task scheduling — are the same patterns you can build in plain Python.

What CrewAI does

CrewAI models multi-agent systems as a crew of specialists. Each Agent has a role ("Senior Researcher"), a goal ("Find the best data sources"), a backstory that shapes its behavior, and a set of tools it can use. Tasks define discrete units of work with expected outputs. The Crew orchestrates execution — sequentially, hierarchically, or with a custom process. CrewAI also provides memory systems (short-term, long-term, entity) and delegation, where one agent can hand off subtasks to another. The mental model is a team of people collaborating on a project. For prototyping multi-agent workflows where you want to reason about roles and responsibilities, it provides a clean vocabulary.

The plain Python equivalent

An Agent in CrewAI is a function with a system prompt that includes the role, goal, and backstory. The tools dict maps names to callables. Task delegation is a list of tasks processed in order — each task calls the assigned agent function with the task description appended to the messages. Hierarchical execution is a manager agent that decides which sub-agent to call next (just another tool choice). Memory is a dict injected into the system prompt. The entire crew pattern — multiple agents, task queue, delegation — is a for-loop over tasks, where each iteration calls the right agent function. No Crew class, no process kwarg. Just functions calling functions with a shared state dict passed between them.

Full CrewAI comparison →

Or build your own in 60 lines

Both Agno and CrewAI implement the same 8 patterns. An agent is a function. Tools are a dict. The loop is a while loop. The whole thing composes in ~60 lines of Python.

No framework. No dependencies. No opinions. Just the code.

Build it from scratch →