agno 2.0.1__py3-none-any.whl → 2.3.0__py3-none-any.whl

{agno-2.0.1.dist-info → agno-2.3.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agno
-Version: 2.0.1
+Version: 2.3.0
 Summary: Agno: a lightweight library for building Multi-Agent Systems
 Author-email: Ashpreet Bedi <ashpreet@agno.com>
 Project-URL: homepage, https://agno.com
@@ -23,7 +23,8 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: docstring-parser
 Requires-Dist: gitpython
-Requires-Dist: httpx
+Requires-Dist: h11>=0.16.0
+Requires-Dist: httpx[http2]
 Requires-Dist: packaging
 Requires-Dist: pydantic-settings
 Requires-Dist: pydantic
@@ -34,12 +35,12 @@ Requires-Dist: rich
 Requires-Dist: typer
 Requires-Dist: typing-extensions
 Provides-Extra: dev
-Requires-Dist: mypy; extra == "dev"
+Requires-Dist: mypy==1.18.2; extra == "dev"
+Requires-Dist: ruff==0.14.3; extra == "dev"
 Requires-Dist: pytest; extra == "dev"
 Requires-Dist: pytest-asyncio; extra == "dev"
 Requires-Dist: pytest-cov; extra == "dev"
 Requires-Dist: pytest-mock; extra == "dev"
-Requires-Dist: ruff; extra == "dev"
 Requires-Dist: timeout-decorator; extra == "dev"
 Requires-Dist: types-pyyaml; extra == "dev"
 Requires-Dist: types-aiofiles; extra == "dev"
@@ -48,12 +49,14 @@ Requires-Dist: uvicorn; extra == "dev"
 Provides-Extra: os
 Requires-Dist: fastapi; extra == "os"
 Requires-Dist: uvicorn; extra == "os"
+Requires-Dist: PyJWT; extra == "os"
 Provides-Extra: integration-tests
 Requires-Dist: exa_py; extra == "integration-tests"
 Requires-Dist: ddgs; extra == "integration-tests"
 Requires-Dist: yfinance; extra == "integration-tests"
 Requires-Dist: sqlalchemy; extra == "integration-tests"
 Requires-Dist: Pillow; extra == "integration-tests"
+Requires-Dist: fastmcp; extra == "integration-tests"
 Provides-Extra: opentelemetry
 Requires-Dist: opentelemetry-sdk; extra == "opentelemetry"
 Requires-Dist: opentelemetry-exporter-otlp; extra == "opentelemetry"
@@ -132,6 +135,8 @@ Provides-Extra: fal
 Requires-Dist: fal_client; extra == "fal"
 Provides-Extra: firecrawl
 Requires-Dist: firecrawl-py; extra == "firecrawl"
+Provides-Extra: tavily
+Requires-Dist: tavily-python; extra == "tavily"
 Provides-Extra: crawl4ai
 Requires-Dist: crawl4ai; extra == "crawl4ai"
 Provides-Extra: github
@@ -156,11 +161,19 @@ Requires-Dist: memorisdk; extra == "memori"
 Provides-Extra: newspaper
 Requires-Dist: newspaper4k; extra == "newspaper"
 Requires-Dist: lxml_html_clean; extra == "newspaper"
+Provides-Extra: notion
+Requires-Dist: notion-client; extra == "notion"
 Provides-Extra: opencv
 Requires-Dist: opencv-python; extra == "opencv"
+Provides-Extra: parallel
+Requires-Dist: parallel-web; extra == "parallel"
 Provides-Extra: psycopg
 Requires-Dist: psycopg-binary; extra == "psycopg"
 Requires-Dist: psycopg; extra == "psycopg"
+Provides-Extra: reportlab
+Requires-Dist: reportlab; extra == "reportlab"
+Provides-Extra: scrapegraph
+Requires-Dist: scrapegraph-py; extra == "scrapegraph"
 Provides-Extra: todoist
 Requires-Dist: todoist-api-python; extra == "todoist"
 Provides-Extra: valyu
@@ -185,6 +198,11 @@ Provides-Extra: sql
 Requires-Dist: sqlalchemy; extra == "sql"
 Provides-Extra: postgres
 Requires-Dist: psycopg-binary; extra == "postgres"
+Provides-Extra: async-postgres
+Requires-Dist: asyncpg; extra == "async-postgres"
+Provides-Extra: async-mongo
+Requires-Dist: pymongo; extra == "async-mongo"
+Requires-Dist: motor; extra == "async-mongo"
 Provides-Extra: sqlite
 Requires-Dist: sqlalchemy; extra == "sqlite"
 Provides-Extra: gcs
@@ -193,6 +211,7 @@ Provides-Extra: firestore
 Requires-Dist: google-cloud-firestore; extra == "firestore"
 Provides-Extra: redis
 Requires-Dist: redis; extra == "redis"
+Requires-Dist: redisvl; extra == "redis"
 Provides-Extra: pgvector
 Requires-Dist: pgvector; extra == "pgvector"
 Provides-Extra: chromadb
@@ -229,6 +248,8 @@ Requires-Dist: pypdf; extra == "pdf"
 Requires-Dist: rapidocr_onnxruntime; extra == "pdf"
 Provides-Extra: docx
 Requires-Dist: python-docx; extra == "docx"
+Provides-Extra: pptx
+Requires-Dist: python-pptx; extra == "pptx"
 Provides-Extra: text
 Requires-Dist: aiofiles; extra == "text"
 Provides-Extra: csv
@@ -242,6 +263,8 @@ Requires-Dist: chonkie[st]; extra == "chonkie"
 Requires-Dist: chonkie; extra == "chonkie"
 Provides-Extra: agui
 Requires-Dist: ag-ui-protocol; extra == "agui"
+Provides-Extra: a2a
+Requires-Dist: a2a-sdk; extra == "a2a"
 Provides-Extra: huggingface
 Requires-Dist: huggingface-hub; extra == "huggingface"
 Provides-Extra: performance
@@ -262,7 +285,6 @@ Requires-Dist: agno[anthropic]; extra == "models"
 Requires-Dist: agno[azure]; extra == "models"
 Requires-Dist: agno[cerebras]; extra == "models"
 Requires-Dist: agno[cohere]; extra == "models"
-Requires-Dist: agno[infinity]; extra == "models"
 Requires-Dist: agno[google]; extra == "models"
 Requires-Dist: agno[groq]; extra == "models"
 Requires-Dist: agno[ibm]; extra == "models"
@@ -284,6 +306,7 @@ Requires-Dist: agno[duckdb]; extra == "tools"
 Requires-Dist: agno[newspaper]; extra == "tools"
 Requires-Dist: agno[youtube]; extra == "tools"
 Requires-Dist: agno[firecrawl]; extra == "tools"
+Requires-Dist: agno[tavily]; extra == "tools"
 Requires-Dist: agno[crawl4ai]; extra == "tools"
 Requires-Dist: agno[github]; extra == "tools"
 Requires-Dist: agno[gmail]; extra == "tools"
@@ -298,19 +321,25 @@ Requires-Dist: agno[mcp]; extra == "tools"
 Requires-Dist: agno[browserbase]; extra == "tools"
 Requires-Dist: agno[agentql]; extra == "tools"
 Requires-Dist: agno[opencv]; extra == "tools"
+Requires-Dist: agno[parallel]; extra == "tools"
+Requires-Dist: agno[scrapegraph]; extra == "tools"
 Requires-Dist: agno[valyu]; extra == "tools"
 Requires-Dist: agno[confluence]; extra == "tools"
+Requires-Dist: agno[notion]; extra == "tools"
 Requires-Dist: agno[oxylabs]; extra == "tools"
 Requires-Dist: agno[zep]; extra == "tools"
 Requires-Dist: agno[mem0]; extra == "tools"
 Requires-Dist: agno[memori]; extra == "tools"
 Requires-Dist: agno[google_bigquery]; extra == "tools"
 Requires-Dist: agno[psycopg]; extra == "tools"
+Requires-Dist: agno[reportlab]; extra == "tools"
 Requires-Dist: agno[trafilatura]; extra == "tools"
 Requires-Dist: agno[neo4j]; extra == "tools"
 Provides-Extra: storage
 Requires-Dist: agno[sql]; extra == "storage"
 Requires-Dist: agno[postgres]; extra == "storage"
+Requires-Dist: agno[async_postgres]; extra == "storage"
+Requires-Dist: agno[async_mongo]; extra == "storage"
 Requires-Dist: agno[sqlite]; extra == "storage"
 Requires-Dist: agno[gcs]; extra == "storage"
 Requires-Dist: agno[firestore]; extra == "storage"
@@ -333,12 +362,14 @@ Requires-Dist: agno[upstash]; extra == "vectordbs"
 Provides-Extra: knowledge
 Requires-Dist: agno[pdf]; extra == "knowledge"
 Requires-Dist: agno[docx]; extra == "knowledge"
+Requires-Dist: agno[pptx]; extra == "knowledge"
 Requires-Dist: agno[text]; extra == "knowledge"
 Requires-Dist: agno[csv]; extra == "knowledge"
 Requires-Dist: agno[markdown]; extra == "knowledge"
 Requires-Dist: agno[chonkie]; extra == "knowledge"
 Provides-Extra: embedders
 Requires-Dist: agno[huggingface]; extra == "embedders"
+Requires-Dist: agno[vllm]; extra == "embedders"
 Provides-Extra: tests
 Requires-Dist: agno[dev]; extra == "tests"
 Requires-Dist: agno[models]; extra == "tests"
@@ -355,7 +386,7 @@ Requires-Dist: build; extra == "tests"
 Dynamic: license-file
 
 <div align="center" id="top">
-  <a href="https://docs.agno.com">
+  <a href="https://agno.com">
     <picture>
       <source media="(prefers-color-scheme: dark)" srcset="https://agno-public.s3.us-east-1.amazonaws.com/assets/logo-dark.svg">
       <source media="(prefers-color-scheme: light)" srcset="https://agno-public.s3.us-east-1.amazonaws.com/assets/logo-light.svg">
@@ -363,61 +394,131 @@ Dynamic: license-file
     </picture>
   </a>
 </div>
+
 <div align="center">
-  <a href="https://docs.agno.com">📚 Documentation</a> &nbsp;|&nbsp;
-  <a href="https://docs.agno.com/examples/introduction">💡 Examples</a> &nbsp;|&nbsp;
-  <a href="https://github.com/agno-agi/agno/stargazers">🌟 Star Us</a>
+  <a href="https://docs.agno.com">Documentation</a>
+  <span>&nbsp;&nbsp;•&nbsp;&nbsp;</span>
+  <a href="https://docs.agno.com/examples/introduction">Examples</a>
+  <span>&nbsp;&nbsp;•&nbsp;&nbsp;</span>
+  <a href="https://www.agno.com/?utm_source=github&utm_medium=readme&utm_campaign=agno-github">Website</a>
+  <br />
 </div>
 
 ## What is Agno?
 
-[Agno](https://docs.agno.com) is a high-performance runtime for multi-agent systems. Use it to build, run and manage secure multi-agent systems in your cloud.
+Agno is a multi-agent framework, runtime and control plane. Built for speed, privacy, and scale.
+
+It provides a rich set of tools for building:
+
+- **Agents** with memory, knowledge, session management, and advanced features like human-in-the-loop, guardrails, dynamic context management and best-in-class MCP support.
+- **Multi-Agent Teams** that operate autonomously under a team leader that maintains shared state and context. Perfect for use cases where the scope exceeds beyond a single agent.
+- **Step-based Workflows** for controlled, deterministic execution. Steps can be Agents, Teams, or regular python functions that run sequentially, in parallel, in loops, branches, or conditionally.
+
+Agno also provides a ready-to-use FastAPI app (called the AgentOS) for serving your agents, teams and workflows in production. Stateless, horizontally scalable and designed for scale, the AgentOS gives you major head start in building your AI product.
+
+## Getting started
+
+If you're new to Agno, follow our [quickstart](https://docs.agno.com/introduction/quickstart) to build your first Agent and chat with it using the AgentOS UI.
+
+After that, checkout the [examples gallery](https://docs.agno.com/examples/introduction) and build real-world applications with Agno.
+
+## Documentation, Community & More Examples
+
+- Docs: <a href="https://docs.agno.com" target="_blank" rel="noopener noreferrer">docs.agno.com</a>
+- Cookbook: <a href="https://github.com/agno-agi/agno/tree/main/cookbook" target="_blank" rel="noopener noreferrer">Cookbook</a>
+- Community forum: <a href="https://community.agno.com/" target="_blank" rel="noopener noreferrer">community.agno.com</a>
+- Discord: <a href="https://discord.gg/4MtYHHrgA8" target="_blank" rel="noopener noreferrer">discord</a>
 
-Agno gives you the fastest framework for building agents with session management, memory, knowledge, human in the loop and MCP support. You can put agents together as an autonomous multi-agent team, or build step-based agentic workflows for full control over complex multi-step processes.
+## Example
 
-In 10 lines of code, we can build an Agent that will fetch the top stories from HackerNews and summarize them.
+Here’s an example of an Agent that connects to an MCP server, manages conversation state in a database, is served using a FastAPI application that you can chat with using the [AgentOS UI](https://os.agno.com).
 
-```python hackernews_agent.py
+```python agno_agent.py
 from agno.agent import Agent
+from agno.db.sqlite import SqliteDb
 from agno.models.anthropic import Claude
-from agno.tools.hackernews import HackerNewsTools
-
-agent = Agent(
-    model=Claude(id="claude-sonnet-4-0"),
-    tools=[HackerNewsTools()],
+from agno.os import AgentOS
+from agno.tools.mcp import MCPTools
+
+# ************* Create Agent *************
+agno_agent = Agent(
+    name="Agno Agent",
+    model=Claude(id="claude-sonnet-4-5"),
+    # Add a database to the Agent
+    db=SqliteDb(db_file="agno.db"),
+    # Add the Agno MCP server to the Agent
+    tools=[MCPTools(transport="streamable-http", url="https://docs.agno.com/mcp")],
+    # Add the previous session history to the context
+    add_history_to_context=True,
     markdown=True,
 )
-agent.print_response("Summarize the top 5 stories on hackernews", stream=True)
+
+
+# ************* Create AgentOS *************
+agent_os = AgentOS(agents=[agno_agent])
+# Get the FastAPI app for the AgentOS
+app = agent_os.get_app()
+
+# ************* Run AgentOS *************
+if __name__ == "__main__":
+    agent_os.serve(app="agno_agent:app", reload=True)
 ```
 
-But the real advantage of Agno is its [AgentOS](https://docs.agno.com/agent-os/introduction) runtime:
+## AgentOS - Production Runtime for Multi-Agent Systems
 
-1. You get a pre-built FastAPI app for running your agentic system, meaning you start building your product on day one. This is a remarkable advantage over other solutions or rolling your own.
-2. You also get a control plane which connects directly to your AgentOS for testing, monitoring and managing your system. This gives you unmatched visibility and control over your system.
-3. Your AgentOS runs in your cloud and you get complete data privacy because no data ever leaves your system. This is incredible for security conscious enterprises that can't send traces to external services.
+Building Agents is easy, running them is hard, and that's where the AgentOS comes in. AgentOS is a high-performance runtime for serving multi-agent systems in production. Key features include:
 
-For organizations building agents, Agno provides the complete solution. You get the fastest framework for building agents (speed of development and execution), a pre-built FastAPI app that lets you build your product on day one, and a control plane for managing your system.
+1. **Pre-built FastAPI app**: AgentOS ships with a ready-to-use FastAPI app for orchestrating your agents, teams, and workflows. This gives you a major head start in building your AI product.
 
-We bring a novel architecture that no other framework provides, your AgentOS runs securely in your cloud, and the control plane connects directly to it from your browser. You don't need to send data to external services or pay retention costs, you get complete privacy and control.
+2. **Integrated Control Plane**: The [AgentOS UI](https://os.agno.com) connects directly to your runtime, letting you test, monitor, and manage your system in real time, giving you unmatched control over your system.
 
-## Getting started
+3. **Private by Design**: AgentOS runs entirely in your cloud, ensuring complete data privacy. No data ever leaves your system. This is ideal for security-conscious enterprises.
 
-If you're new to Agno, follow our [quickstart](https://docs.agno.com/introduction/quickstart) to build your first Agent and run it using the AgentOS.
+Here's what the [AgentOS UI](https://os.agno.com) looks like in action:
 
-After that, checkout the [examples gallery](https://docs.agno.com/examples/introduction) and build real-world applications with Agno.
+https://github.com/user-attachments/assets/feb23db8-15cc-4e88-be7c-01a21a03ebf6
 
-## Documentation, Community & More examples
+## The Complete Agentic Solution
 
-- Docs: <a href="https://docs.agno.com" target="_blank" rel="noopener noreferrer">docs.agno.com</a>
-- Cookbook: <a href="https://github.com/agno-agi/agno/tree/main/cookbook" target="_blank" rel="noopener noreferrer">Cookbook</a>
-- Community forum: <a href="https://community.agno.com/" target="_blank" rel="noopener noreferrer">community.agno.com</a>
-- Discord: <a href="https://discord.gg/4MtYHHrgA8" target="_blank" rel="noopener noreferrer">discord</a>
+For companies building agents, Agno provides the complete agentic solution:
+
+- The fastest framework for building agents, multi-agent teams and agentic workflows.
+- A ready-to-use FastAPI app that gets you building AI products on day one.
+- A control plane for testing, monitoring and managing your system.
+
+Agno brings a novel architecture that no other framework provides, your AgentOS runs securely in your cloud, and the control plane connects directly to it from your browser. You don't need to send data to any external services or pay retention costs, you get complete privacy and control.
+
+## Designed for Agent Engineering
+
+Agno is an incredibly feature-rich framework, designed for Agent Engineering. Here are some key features:
 
-## Setup your coding agent to use Agno
+| **Category** | **Feature** | **Description** |
+|---------------|-------------|-----------------|
+| **Core Intelligence** | **Model Agnostic** | Works with any model provider so you can use your favorite LLMs. |
+|  | **Type Safe** | Enforce structured I/O through `input_schema` and `output_schema` for predictable, composable behavior. |
+|  | **Dynamic Context Engineering** | Inject variables, state, and retrieved data on the fly into context. Perfect for dependency-driven agents. |
+| **Memory, Knowledge, and Persistence** | **Persistent Storage** | Give your Agents, Teams, and Workflows a database to persist session history, state, and messages. |
+|  | **User Memory** | Built-in memory system that allows Agents to recall user-specific context across sessions. |
+|  | **Agentic RAG** | Connect to 20+ vector stores (called **Knowledge** in Agno) with hybrid search + reranking out of the box. |
+|  | **Culture (Collective Memory)** | Shared knowledge that compounds across agents and time. |
+| **Execution & Control** | **Human-in-the-Loop** | Native support for confirmations, manual overrides, and external tool execution. |
+|  | **Guardrails** | Built-in safeguards for validation, security, and prompt protection. |
+|  | **Agent Lifecycle Hooks** | Pre- and post-hooks to validate or transform inputs and outputs. |
+|  | **MCP Integration** | First-class support for the Model Context Protocol (MCP) to connect Agents with external systems. |
+|  | **Toolkits** | 100+ built-in toolkits with thousands of tools, ready for use across data, code, web, and enterprise APIs. |
+| **Runtime & Evaluation** | **Runtime** | Pre-built FastAPI based runtime with SSE compatible endpoints, ready for production on day 1. |
+|  | **Control Plane (UI)** | Integrated interface to visualize, monitor, and debug agent activity in real time. |
+|  | **Natively Multimodal** | Agents can process and generate text, images, audio, video, and files. |
+|  | **Evals** | Measure your Agents' Accuracy, Performance, and Reliability. |
+| **Security & Privacy** | **Private by Design** | Runs entirely in your cloud. The UI connects directly to your AgentOS from your browser, no data is ever sent externally. |
+|  | **Data Governance** | Your data lives securely in your Agent database, no external data sharing or vendor lock-in. |
+|  | **Access Control** | Role-based access (RBAC) and per-agent permissions to protect sensitive contexts and tools. |
 
-For LLMs and AI assistants to understand and navigate Agno's documentation, we provide an [llms.txt](https://docs.agno.com/llms.txt) or [llms-full.txt](https://docs.agno.com/llms-full.txt) file.
+Every part of Agno is built for real-world deployment — where developer experience meets production performance.
 
-This file is built for AI systems to efficiently parse and reference our documentation.
+## Setup Your Coding Agent to Use Agno
+
+For LLMs and AI assistants to understand and navigate Agno's documentation, we provide an [llms.txt](https://docs.agno.com/llms.txt) or [llms-full.txt](https://docs.agno.com/llms-full.txt) file. This file is built for AI systems to efficiently parse and reference our documentation.
 
 ### IDE Integration
 
@@ -432,54 +533,77 @@ Now, Cursor will have access to the Agno documentation. You can do the same with
 
 ## Performance
 
-At Agno, we're obsessed with performance. Why? because even simple AI workflows can spawn thousands of Agents. Scale that to a modest number of users and performance becomes a bottleneck. Agno is designed for building highly performant agentic systems:
+If you're building with Agno, you're guaranteed best-in-class performance by default. Our obsession with performance is necessary because even simple AI workflows can spawn hundreds of Agents and because many tasks are long-running -- stateless, horizontal scalability is key for success.
+
+At Agno, we optimize performance across 3 dimensions:
+
+1. **Agent performance:** We optimize static operations (instantiation, memory footprint) and runtime operations (tool calls, memory updates, history management).
+2. **System performance:** The AgentOS API is async by default and has a minimal memory footprint. The system is stateless and horizontally scalable, with a focus on preventing memory leaks. It handles parallel and batch embedding generation during knowledge ingestion, metrics collection in background tasks, and other system-level optimizations.
+3. **Agent reliability and accuracy:** Monitored through evals, which we’ll explore later.
+
+### Agent Performance
+
+Let's measure the time it takes to instantiate an Agent and the memory footprint of an Agent. Here are the numbers (last measured in Oct 2025, on an Apple M4 MacBook Pro):
 
-- Agent instantiation: ~3μs on average
-- Memory footprint: ~6.5Kib on average
+- **Agent instantiation:** ~3μs on average
+- **Memory footprint:** ~6.6Kib on average
 
-> Tested on an Apple M4 Mackbook Pro.
+We'll show below that Agno Agents instantiate **529× faster than Langgraph**, **57× faster than PydanticAI**, and **70× faster than CrewAI**. Agno Agents also use **24× lower memory than Langgraph**, **4× lower than PydanticAI**, and **10× lower than CrewAI**.
 
-While an Agent's run-time is bottlenecked by inference, we must do everything possible to minimize execution time, reduce memory usage, and parallelize tool calls. These numbers may seem trivial at first, but our experience shows that they add up even at a reasonably small scale.
+> [!NOTE]
+> Run time performance is bottlenecked by inference and hard to benchmark accurately, so we focus on minimizing overhead, reducing memory usage, and parallelizing tool calls.
 
-### Instantiation time
+### Instantiation Time
 
-Let's measure the time it takes for an Agent with 1 tool to start up. We'll run the evaluation 1000 times to get a baseline measurement.
+Let's measure instantiation time for an Agent with 1 tool. We'll run the evaluation 1000 times to get a baseline measurement. We'll compare Agno to LangGraph, CrewAI and Pydantic AI.
 
-You should run the evaluation yourself on your own machine, please, do not take these results at face value.
+> [!NOTE]
+> The code for this benchmark is available [here](https://github.com/agno-agi/agno/tree/main/cookbook/evals/performance). You should run the evaluation yourself on your own machine, please, do not take these results at face value.
 
 ```shell
 # Setup virtual environment
 ./scripts/perf_setup.sh
 source .venvs/perfenv/bin/activate
-# OR Install dependencies manually
-# pip install openai agno langgraph langchain_openai
 
 # Agno
-python evals/performance/instantiation_with_tool.py
+python cookbook/evals/performance/instantiate_agent_with_tool.py
 
 # LangGraph
-python evals/performance/other/langgraph_instantiation.py
+python cookbook/evals/performance/comparison/langgraph_instantiation.py
+# CrewAI
+python cookbook/evals/performance/comparison/crewai_instantiation.py
+# Pydantic AI
+python cookbook/evals/performance/comparison/pydantic_ai_instantiation.py
 ```
 
-> The following evaluation is run on an Apple M4 Mackbook Pro. It also runs as a Github action on this repo.
+LangGraph is on the right, **let's start it first and give it a head start**. Then CrewAI and Pydantic AI follow, and finally Agno. Agno obviously finishes first, but let's see by how much.
 
-LangGraph is on the right, **let's start it first and give it a head start**.
+https://github.com/user-attachments/assets/54b98576-1859-4880-9f2d-15e1a426719d
 
-Agno is on the left, notice how it finishes before LangGraph gets 1/2 way through the runtime measurement, and hasn't even started the memory measurement. That's how fast Agno is.
-
-https://github.com/user-attachments/assets/ba466d45-75dd-45ac-917b-0a56c5742e23
-
-### Memory usage
+### Memory Usage
 
 To measure memory usage, we use the `tracemalloc` library. We first calculate a baseline memory usage by running an empty function, then run the Agent 1000x times and calculate the difference. This gives a (reasonably) isolated measurement of the memory usage of the Agent.
 
 We recommend running the evaluation yourself on your own machine, and digging into the code to see how it works. If we've made a mistake, please let us know.
 
-### Conclusion
+### Results
+
+Taking Agno as the baseline, we can see that:
+
+| Metric             | Agno | Langgraph   | PydanticAI | CrewAI     |
+| ------------------ | ---- | ----------- | ---------- | ---------- |
+| **Time (seconds)** | 1×   | 529× slower | 57× slower | 70× slower |
+| **Memory (MiB)**   | 1×   | 24× higher  | 4× higher  | 10× higher |
+
+Exact numbers from the benchmark:
 
-Agno agents are designed for performance and while we do share some benchmarks against other frameworks, we should be mindful that accuracy and reliability are more important than speed.
+| Metric             | Agno     | Langgraph | PydanticAI | CrewAI   |
+| ------------------ | -------- | --------- | ---------- | -------- |
+| **Time (seconds)** | 0.000003 | 0.001587  | 0.000170   | 0.000210 |
+| **Memory (MiB)**   | 0.006642 | 0.161435  | 0.028712   | 0.065652 |
 
-Given that each framework is different and we won't be able to tune their performance like we do with Agno, for future benchmarks we'll only be comparing against ourselves.
+> [!NOTE]
+> Agno agents are designed for performance and while we share benchmarks against other frameworks, we should be mindful that accuracy and reliability are more important than speed.
 
 ## Contributions