AdalFlow

AdalFlow: The library to build & auto-optimize LLM applications.

Generate Convert Improve

Install / Use

/learn @SylphAI-Inc/AdalFlow

About this skill

Quality Score

0/100

README

<h2> <p align="center"> ⚡ AdalFlow is a PyTorch-like library to build and auto-optimize any LM workflows, from Chatbots, RAG, to Agents. ⚡ </p> </h2> <p align="center"> <a href="https://sylph.ai"><img src="docs/source/_static/images/adal-face-logo.svg" alt="AdaL" height="100"></a>  <a href="https://sylph.ai"><img src="docs/source/_static/images/adal-text-logo.svg" alt="AdaL CLI" height="100"></a> <br><br> <strong>AdalFlow proudly powers <a href="https://sylph.ai">AdaL CLI</a></strong> — The AI coding agent </p> <p align="center"> <a href="https://colab.research.google.com/drive/1_YnD4HshzPRARvishoU4IA-qQuX9jHrT?usp=sharing"> <img alt="Try Quickstart in Colab" src="https://colab.research.google.com/assets/colab-badge.svg"> </a> </p> <h4 align="center"> <p> <a href="https://adalflow.sylph.ai/">View Documentation</a>  <p> </h4> <p align="center"> <a href="https://pypi.org/project/adalflow/"> <img alt="PyPI Version" src="https://img.shields.io/pypi/v/adalflow?style=flat-square"> </a> <a href="https://pypi.org/project/adalflow/"> <img alt="PyPI Downloads" src="https://static.pepy.tech/badge/adalflow"> </a> <a href="https://pypi.org/project/adalflow/"> <img alt="PyPI Downloads" src="https://static.pepy.tech/badge/adalflow/month"> </a> <a href="https://star-history.com/#SylphAI-Inc/AdalFlow"> <img alt="GitHub stars" src="https://img.shields.io/github/stars/SylphAI-Inc/AdalFlow?style=flat-square"> </a> <a href="https://github.com/SylphAI-Inc/AdalFlow/issues"> <img alt="Open Issues" src="https://img.shields.io/github/issues-raw/SylphAI-Inc/AdalFlow?style=flat-square"> </a> <a href="https://opensource.org/license/MIT"> <img alt="License" src="https://img.shields.io/github/license/SylphAI-Inc/AdalFlow"> </a> <a href="https://discord.gg/ezzszrRZvT"> <img alt="discord-invite" src="https://dcbadge.limes.pink/api/server/ezzszrRZvT?style=flat"> </a> </p>

Why AdalFlow

100% Open-source Agents SDK: Lightweight and requires no additional API to setup Human-in-the-Loop and Tracing Functionalities.
Say goodbye to manual prompting: AdalFlow provides a unified auto-differentiative framework for both zero-shot optimization and few-shot prompt optimization. Our research, LLM-AutoDiff and Learn-to-Reason Few-shot In Context Learning, achieve the highest accuracy among all auto-prompt optimization libraries.
Switch your LLM app to any model via a config: AdalFlow provides Model-agnostic building blocks for LLM task pipelines, ranging from RAG, Agents to classical NLP tasks.

<p align="center" style="background-color: #f0f0f0;"> <img src="https://raw.githubusercontent.com/SylphAI-Inc/AdalFlow/main/docs/source/_static/images/classification_opt_prompt.png" alt="AdalFlow Optimized Prompt" style="width: 80%;"> </p> <p align="center" style="background-color: #f0f0f0;"> <img src="https://raw.githubusercontent.com/SylphAI-Inc/AdalFlow/main/docs/source/_static/images/adalflow_tracing_mlflow.png" alt="AdalFlow MLflow Integration" style="width: 80%;"> </p>

View Documentation

Quick Start

Install AdalFlow with pip:

pip install adalflow

Hello World Agent Example

from adalflow import Agent, Runner
from adalflow.components.model_client.openai_client import OpenAIClient
from adalflow.core.types import (
    ToolCallActivityRunItem, 
    RunItemStreamEvent,
    ToolCallRunItem,
    ToolOutputRunItem,
    FinalOutputItem
)
import asyncio

# Define tools
def calculator(expression: str) -> str:
    """Evaluate a mathematical expression."""
    try:
        result = eval(expression)
        return f"The result of {expression} is {result}"
    except Exception as e:
        return f"Error: {e}"

async def web_search(query: str="what is the weather in SF today?") -> str:
    """Web search on query."""
    await asyncio.sleep(0.5)
    return "San Francisco will be mostly cloudy today with some afternoon sun, reaching about 67 °F (20 °C)."

def counter(limit: int):
    """A counter that counts up to a limit."""
    final_output = []
    for i in range(1, limit + 1):
        stream_item = f"Count: {i}/{limit}"
        final_output.append(stream_item)
        yield ToolCallActivityRunItem(data=stream_item)
    yield final_output

# Create agent with tools
agent = Agent(
    name="MyAgent",
    tools=[calculator, web_search, counter],
    model_client=OpenAIClient(),
    model_kwargs={"model": "gpt-4o", "temperature": 0.3},
    max_steps=5
)

runner = Runner(agent=agent)

1. Synchronous Call Mode

# Sync call - returns RunnerResult with complete execution history
result = runner.call(
    prompt_kwargs={"input_str": "Calculate 15 * 7 + 23 and count to 5"}
)

print(result.answer)
# Output: The result of 15 * 7 + 23 is 128. The counter counted up to 5: 1, 2, 3, 4, 5.

# Access step history
for step in result.step_history:
    print(f"Step {step.step}: {step.function.name} -> {step.observation}")
# Output:
# Step 0: calculator -> The result of 15 * 7 + 23 is 128
# Step 1: counter -> ['Count: 1/5', 'Count: 2/5', 'Count: 3/5', 'Count: 4/5', 'Count: 5/5']

2. Asynchronous Call Mode

# Async call - similar output structure to sync call
result = await runner.acall(
    prompt_kwargs={"input_str": "What's the weather in SF and calculate 42 * 3"}
)

print(result.answer)
# Output: San Francisco will be mostly cloudy today with some afternoon sun, reaching about 67 °F (20 °C). 
#         The result of 42 * 3 is 126.

3. Async Streaming Mode

# Async streaming - real-time event processing
streaming_result = runner.astream(
    prompt_kwargs={"input_str": "Calculate 100 + 50 and count to 3"},
)

# Process streaming events in real-time
async for event in streaming_result.stream_events():
    if isinstance(event, RunItemStreamEvent):
        if isinstance(event.item, ToolCallRunItem):
            print(f"🔧 Calling: {event.item.data.name}")
        elif isinstance(event.item, ToolCallActivityRunItem):
            print(f"📝 Activity: {event.item.data}")
        elif isinstance(event.item, ToolOutputRunItem):
            print(f"✅ Output: {event.item.data.output}")
        elif isinstance(event.item, FinalOutputItem):
            print(f"🎯 Final: {event.item.data.answer}")

# Output:
# 🔧 Calling: calculator
# ✅ Output: The result of 100 + 50 is 150
# 🔧 Calling: counter
# 📝 Activity: Count: 1/3
# 📝 Activity: Count: 2/3
# 📝 Activity: Count: 3/3
# ✅ Output: ['Count: 1/3', 'Count: 2/3', 'Count: 3/3']
# 🎯 Final: The result of 100 + 50 is 150. Counted to 3 successfully.

Set your OPENAI_API_KEY environment variable to run these examples.

Try the full Agent tutorial in Colab:

View Quickstart: Learn How AdalFlow optimizes LM workflows end-to-end in 15 mins.

Go to Documentation for tracing, human-in-the-loop, and more.

<!-- * Try the [Building Quickstart](https://colab.research.google.com/drive/1TKw_JHE42Z_AWo8UuRYZCO2iuMgyslTZ?usp=sharing) in Colab to see how AdalFlow can build the task pipeline, including Chatbot, RAG, agent, and structured output. * Try the [Optimization Quickstart](https://colab.research.google.com/github/SylphAI-Inc/AdalFlow/blob/main/notebooks/qas/adalflow_object_count_auto_optimization.ipynb) to see how AdalFlow can optimize the task

Related Skills

claude-opus-4-5-migration

83.2k

Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5

model-usage

337.3k

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

openhue

337.3k

Control Philips Hue lights and scenes via the OpenHue CLI.

sag

337.3k

ElevenLabs text-to-speech with mac-style say UX.