9 must-know dev tools to build cool AI apps 🧙♂️🪄
I have been working with AI applications for a long time. I have built multiple AI-driven applications, and during the development process, I often face challenges, such as:
- Integrating the AI functionality
- Handling the authorization
- Managing the AI workflow
In this blog, I have curated a list of AI tools that can be used to overcome these problems.
1. AgentAuth - Auth simplified for AI Agents
Managing authentication is one of the major problems I have faced while building AI applications. Traditional authentication methods often fail in AI applications due to multiple challenges. AgentAuth helps us with this.
AgentAuth simplifies the management of authentication workflows for AI agents by offering a developer-centric platform tailored to their needs. It enables developers to build AI agents that can seamlessly interact with integrated external applications on behalf of users.
AgentAuth supports over 250 API integrations, including Google Calendar, Gmail, Discord, Slack, and more. It also provides authentication methods such as API Key, OAuth, JWT, and others.
Other benefits include:
- Compatible with 15+ agentic frameworks - Langchain, CrewAI, Letta, and many more
- Offers a developer-friendly experience by offering Python and JS SDKs that developers can use to integrate AgentAuth
- Strong token management and secure authentication flows guarantee data protection and compliance at every stage.
It’s super easy to get started with AgentAuth.
Install the AgentAuth.
npm install composio-core openai
Authenticate the external application
import { Composio } from "composio-core";
const client = new Composio(COMPOSIO_API_KEY);
const entity = await client.getEntity("Jessica");
const connection = await entity.initiateConnection('googlecalendar');
console.log(`Open this URL to authenticate: ${connection.redirectUrl}`);
Initialize OpenAI and Composio
import { OpenAI } from "openai";
import { OpenAIToolSet } from "composio-core";
const openai_client = new OpenAI({
apiKey: OPENAI_API_KEY
});
const composio_toolset = new OpenAIToolSet({
apiKey: COMPOSIO_API_KEY,
entityId: "Jessica",
});
Fetch the data from the API
const tools = await composio_toolset.getTools({
actions: ["googlecalendar_create_event"]
});
const today = new Date().toDateString();
const instruction = `Create a 1 hour meeting event at 5:30PM tomorrow. Today's date is ${today}`;
const response = await openai_client.chat.completions.create({
model: "gpt-4-turbo-preview",
messages: [{ role: "user", content: instruction }],
tools: tools,
tool_choice: "auto",
});
Finally, execute the action
const result = await composio_toolset.handleToolCall(response);
console.log(result);
To learn more about AgentAuth, check out the official docs.
2. Composio - AI Integration and tooling platform
When it comes to building an AI-enabled application, integrating the AI functionality is the most tricky and important part. That’s where Composio saves us.
Composio is an open-source AI integration platform that helps to create AI agents and integrate into your applications. It comes with multiple integrations including Slack, Discord, Google, Jira, and many more. These integrations can be used to build tailored AI agents.
With Composio, you can take advantage of popular LL Models like Gemini, GPT-4, GPT-4-o, and many more to autonomously run the tasks. Additionally, Composio comes with the support of 15+ frameworks including LangChain, CrewAI, Letta, and many more
For example:
- You can build AI bots for your Slack channels and Discord servers that can autonomously interact with the users and respond to their queries.
- You can build Coding agents to optimize the code present in the Github repository
- AI agent to provide a short summary of reports or documents
Get started with Composio
pip install composio-core
Add a GitHub integration
composio add github
Composio manages user authentication and authorization for you.
Here’s an example to automatically star a GitHub repository using Composio’s GitHub integration:
from openai import OpenAI
from composio_openai import ComposioToolSet, App
openai_client = OpenAI(api_key=OPENAI_API_KEY)
# Initialise the Composio Tool Set
composio_toolset = ComposioToolSet(api_key=COMPOSIO_API_KEY)
## Step 4
# Get GitHub tools that are pre-configured
actions = composio_toolset.get_actions(actions=[Action.GITHUB_ACTIVITY_STAR_REPO_FOR_AUTHENTICATED_USER])
## Step 5
my_task = "Star a repo ComposioHQ/composio on GitHub"
# Create a chat completion request to decide on the action
response = openai_client.chat.completions.create(
model="gpt-4-turbo",
tools=actions, # Passing actions we fetched earlier.
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": my_task}
]
)
Use this Python code to create an AI agent that automatically star a GitHub repository.
Check out the Composio docs to learn more. Explore more advanced examples built using Composio.
Star the Composio repository ⭐
3. Cloudcode - Seamless software Testing
CloudCode is an AI-driven platform designed to optimize software development and deployment processes.
It provides advanced quality assurance tools, automating code reviews, bug detection, and test generation to streamline workflows.
The platform, known as Kaizen, specializes in intelligent pre-deployment code reviews, comprehensive end-to-end testing, and seamless unit test generation.
Kaizen integrates effortlessly with popular development environments and CI/CD pipelines, enabling early error detection and ensuring high-quality, optimized code delivery.
For more details, visit the Cloudcode documentation.
4. Aider - The AI Pair-programmer
If you are into Pair Programming, then Aider is an ideal tool for you. Aider is an AI-enabled pair programming tool that allows the developer to edit the code in the local environment.
You can use Aider in a new project or in an existing project
Aider comes with the support of multiple LLM models that you can connect with your pair programming agent. Some popular LLM models that Aider supports include GPT-4o, Claude 3.5 Sonnet, and many more.
Use the following code to get started with Aider:
pip install aider-chat
# Change the directory into a git repo
cd /to/your/git/repo
# Work with Claude 3.5 Sonnet on your repo
export ANTHROPIC_API_KEY=your-key-goes-here
aider
# Work with GPT-4o on your repo
export OPENAI_API_KEY=your-key-goes-here
aider
Check out the Aider documentation to learn more.
5. Pieces - Your Workflow Copilot
As a developer, managing notes, code files, media assets, and other content while working on a project can be quite challenging. Pieces is the perfect solution for this problem.
Pieces is an AI-driven copilot that simplifies your coding workflow by managing your media files, performing the necessary interactions, and proactively surfacing required materials.
It enhances your overall development experience by understanding the project you're working on and presenting the necessary materials, all while ensuring the security and privacy of your work in a fully offline environment.
Pieces provide many helpful features to boost productivity, such as smart organization of code snippets, useful suggestions based on your work, and easy ways to find the resources you need.
Pieces come with a desktop app that is fully compatible with all Windows, Linux, and Mac OS. It also has an IDE extension that runs on all major IDes including VS Code, Sublime Text, Azure Data Studio, and many more.
Just download the desktop or IDE extension and start using it!
Check out the Pieces documentation to learn more.
6. Continue - Your AI-powered Coding Assistant
Continue is an AI-powered coding assistant designed to understand your coding environment and work seamlessly within it. It functions similarly to the popular Cursor IDE, with the key difference being that Continue is open-source and licensed under the Apache License.
It utilizes leading LLM models, such as OpenAI’s GPT, Google’s Gemini, and others, to understand your development process and enhance your overall coding experience.
You can download and install the Continue extension available on VS Code and Jet Brains IDE.
Some key features:
- Chat feature to understand your code and provide solutions for queries
- Autocomplete the code and provide useful suggestions
- Create customized shortcuts to ease the coding workflow
Go through the Continue documentation to learn more.
Star the Continue Repository ⭐
7. Portkey - Optimize your GenAI Apps
Portkey is an all-in-one platform to manage LLM and simplify the whole process of GenAI application from development to deployment. It offers multiple tools to manage models, maintain privacy, streamline the process, LLM gateway which helps the developers to quickly develop and confidently deploy their AI-powered apps.
Portkey makes it super smooth to introduce AI functionality into your apps by working as a bridge between the AI applications and their providers.
It supports over 250 models, including those from Google Vertex AI, and includes features like semantic caching to lower API costs and enhance response times.
Some key features
- Universal API - integrate with multiple AI models through a single API
- Load Balancing - efficiently distributes the workload across multiple models
- Virtual Keys - easily manage the access of multiple users through virtual API keys
Explore more about the Portkey, visit the docs.
8. AutoCodeRover - Autonomous Program Improvemen
Autocoderover is an AI-driven system that automates the whole process of software development. Solving GitHub issues is the main task that AutoCodeRover is designed for.
It mainly focuses on improving program maintenance by using LLMs along with sophisticated code search techniques. Unlike traditional bug-fixing tools where developers must manually identify bug locations, AutoCodeRover can automatically search for bugs by analyzing the code and identifying the root causes.
The use of LLMs significantly speeds up the entire bug resolution process compared to traditional manual methods. This makes AutoCodeRover a promising tool for developers.
Check out their docs for more information.
Star the AutoCodeRover Repository ⭐
9. Gooey - Low code platform to build AI workflows
Gooey is a low-code AI platform that offers customizable AI workflows, allowing users to build AI systems that can significantly improve service delivery, foster sustainable development, and enhance decision-making.
Gooey is proven to be a very useful tool in multiple sectors, including agriculture, education, and health. For example, Gooey can be used to create multilingual chatbots, allowing farmers to gain access to information in their regional languages.
One of the key features of Gooey is that it provides a robust foundation for AI applications by integrating GPT-based AI models.
Want to learn more Gooey? Check out their docs
Thank you for reading! Do you know any other useful AI tools? Drop them in the comments.