continue

⏩ Create, share, and use custom AI code assistants with our open-source IDE extensions and hub of models, rules, prompts, docs, and other building blocks

27,666

3,134

27,666

1,002

View on GitHub

Top Related Projects

semantic-kernel

25,112

Integrate cutting-edge LLM technology quickly and easily into your apps

langchain

112,766

🦜🔗 Build context-aware reasoning applications

openai-cookbook

64,769

Examples and guides for using the OpenAI API

openai-python

27,567

The official Python library for the OpenAI API

transformers

146,142

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

promptflow

10,504

Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.

Quick Overview

The continuedev/continue repository is a collection of tools and utilities for developers, focused on improving developer productivity and workflow. It includes a variety of command-line tools, scripts, and other resources to help streamline common development tasks.

Pros

Diverse Toolset: The repository offers a wide range of tools and utilities, catering to various development needs, from task automation to project management.
Cross-platform Compatibility: Many of the tools in the repository are designed to work across different operating systems, making them accessible to a broader audience.
Active Development: The project is actively maintained, with regular updates and improvements to the existing tools.
Community Involvement: The repository has a growing community of contributors, ensuring a steady stream of new features and bug fixes.

Cons

Steep Learning Curve: Some of the tools in the repository may have a higher learning curve, requiring users to invest time in understanding their functionality and configuration.
Potential Dependency Issues: As the repository includes a diverse set of tools, there may be compatibility or dependency issues that users need to navigate.
Limited Documentation: While the repository provides some documentation, it may not be comprehensive enough for all users, especially those new to the project.
Potential Overlap with Existing Tools: Some of the tools in the repository may overlap with or duplicate functionality provided by other popular development tools, which could lead to confusion or redundancy.

Code Examples

Since continuedev/continue is a collection of tools and utilities, it does not provide a single code library. However, here are a few examples of the types of tools and scripts you might find in the repository:

Example 1: Task Automation Script

#!/usr/bin/env python
import os
import subprocess

# Change to the project directory
os.chdir('/path/to/project')

# Run linter
subprocess.run(['flake8', '.'], check=True)

# Run tests
subprocess.run(['pytest', 'tests/'], check=True)

# Build the project
subprocess.run(['python', 'setup.py', 'build'], check=True)

# Deploy the project
subprocess.run(['ansible-playbook', 'deploy.yml'], check=True)

This script automates common development tasks, such as running a linter, executing tests, building the project, and deploying it.

Example 2: Git Workflow Helper

#!/bin/bash

# Prompt the user for the branch name
read -p "Enter the branch name: " branch_name

# Create the new branch and switch to it
git checkout -b "$branch_name"

# Add the changes to the staging area
git add .

# Commit the changes
git commit -m "Implement feature: $branch_name"

# Push the new branch to the remote repository
git push -u origin "$branch_name"

This script helps streamline the Git workflow by automating the process of creating a new branch, adding changes, committing, and pushing the branch to the remote repository.

Getting Started

Since continuedev/continue is a collection of tools and utilities, there is no single "getting started" guide. However, you can follow these general steps to get started with the repository:

Clone the repository to your local machine:

git clone https://github.com/continuedev/continue.git

Explore the directory structure and familiarize yourself with the available tools and utilities.
Review the documentation for the specific tools you're interested in using, which can be found in the repository's README or in the individual tool's subdirectories.
Install any dependencies or prerequisites required by the tools you want to use.
Customize the tools to fit your development workflow, if necessary, by modifying the configuration files or scripts.
Start using the tools to automate your development tasks and improve your productivity.
Contribute back to the project by submitting bug reports, feature requests, or even your own tools and utilities.

Competitor Comparisons

semantic-kernel

25,112

Integrate cutting-edge LLM technology quickly and easily into your apps

Pros of Semantic Kernel

More comprehensive framework for building AI applications
Stronger integration with Microsoft's ecosystem and Azure services
Better documentation and examples for enterprise-level development

Cons of Semantic Kernel

Steeper learning curve due to its more complex architecture
Less focus on direct code assistance and IDE integration
Potentially overkill for smaller projects or individual developers

Code Comparison

Semantic Kernel (C#):

var kernel = Kernel.Builder.Build();
var promptTemplate = "{{$input}}";
var function = kernel.CreateSemanticFunction(promptTemplate);
var result = await kernel.RunAsync("Hello, world!", function);

Continue (Python):

from continuedev import ContinueSDK

sdk = ContinueSDK()
result = await sdk.run("Generate a greeting")
print(result.code)

Summary

Semantic Kernel is a more comprehensive framework for building AI-powered applications, with strong Microsoft ecosystem integration. It's well-suited for enterprise-level development but may be complex for smaller projects. Continue, on the other hand, focuses more on direct code assistance and IDE integration, making it potentially more accessible for individual developers or smaller teams working on coding tasks.

langchain

112,766

🦜🔗 Build context-aware reasoning applications

Pros of LangChain

More extensive and mature ecosystem with a wider range of integrations
Stronger community support and documentation
Flexible architecture allowing for easy customization and extension

Cons of LangChain

Steeper learning curve due to its comprehensive nature
Can be overkill for simpler projects or specific use cases
Requires more setup and configuration compared to Continue

Code Comparison

LangChain:

from langchain import OpenAI, LLMChain, PromptTemplate

llm = OpenAI(temperature=0.9)
prompt = PromptTemplate(input_variables=["product"], template="What is a good name for a company that makes {product}?")
chain = LLMChain(llm=llm, prompt=prompt)

print(chain.run("colorful socks"))

Continue:

from continuedev import ContinueClient

client = ContinueClient()
response = client.chat("What is a good name for a company that makes colorful socks?")

print(response)

LangChain offers more granular control over the LLM setup and prompt templating, while Continue provides a simpler, more straightforward interface for quick interactions with the AI model.

openai-cookbook

64,769

Examples and guides for using the OpenAI API

Pros of OpenAI Cookbook

Comprehensive collection of examples and best practices for using OpenAI's APIs
Regularly updated with new features and improvements from OpenAI
Covers a wide range of use cases and applications

Cons of OpenAI Cookbook

Focused solely on OpenAI's offerings, limiting its scope compared to Continue
Less emphasis on IDE integration and developer workflow optimization
May require more setup and configuration for practical use in development environments

Code Comparison

OpenAI Cookbook example (Python):

import openai

response = openai.Completion.create(
  model="text-davinci-002",
  prompt="Translate the following English text to French: '{}'",
  max_tokens=60
)

Continue example (Python):

from continuedev import ContinueClient

client = ContinueClient()
response = client.chat("Translate the following English text to French: '{}'")

The OpenAI Cookbook provides more detailed examples of API usage, while Continue focuses on simplifying the integration of AI assistance into the development workflow.

openai-python

27,567

The official Python library for the OpenAI API

Pros of openai-python

Official OpenAI API client, ensuring reliability and up-to-date features
Comprehensive documentation and examples for easy integration
Supports a wide range of OpenAI models and services

Cons of openai-python

Limited to OpenAI services, lacking support for other AI providers
Requires API key management and potential usage costs
Less focus on developer workflow integration compared to Continue

Code Comparison

Continue:

from continuedev.src.continuedev import Continue

continue_instance = Continue()
result = continue_instance.generate("Write a Python function to calculate factorial")
print(result)

openai-python:

import openai

openai.api_key = "your-api-key"
response = openai.Completion.create(
  engine="text-davinci-002",
  prompt="Write a Python function to calculate factorial",
  max_tokens=100
)
print(response.choices[0].text.strip())

transformers

146,142

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Pros of Transformers

Extensive library of pre-trained models for various NLP tasks
Well-documented and widely adopted in the AI/ML community
Regular updates and contributions from a large open-source community

Cons of Transformers

Steeper learning curve for beginners in NLP
Focused primarily on NLP tasks, limiting its application in other domains
Can be resource-intensive for large models

Code Comparison

Transformers:

from transformers import pipeline

classifier = pipeline("sentiment-analysis")
result = classifier("I love this product!")[0]
print(f"Label: {result['label']}, Score: {result['score']:.4f}")

Continue:

from continuedev import ContinueClient

client = ContinueClient()
response = client.chat("Summarize this text: I love this product!")
print(response)

Key Differences

Transformers is specialized for NLP tasks, while Continue is a more general-purpose AI development tool
Transformers requires more setup and understanding of NLP concepts, whereas Continue aims for a simpler user experience
Continue focuses on integrating AI assistance into the development workflow, while Transformers provides building blocks for NLP models

promptflow

10,504

Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.

Pros of Promptflow

More comprehensive documentation and examples
Stronger integration with Azure services and enterprise environments
Larger community and corporate backing, potentially leading to more frequent updates

Cons of Promptflow

Steeper learning curve due to more complex architecture
Potentially less flexible for quick, local development compared to Continue
Heavier focus on Azure ecosystem may limit some use cases

Code Comparison

Continue:

from continuedev import ContinueClient

client = ContinueClient()
response = client.chat("What is the capital of France?")
print(response)

Promptflow:

from promptflow import PFClient

client = PFClient()
flow = client.flows.get("my_flow")
result = client.test(flow=flow, inputs={"question": "What is the capital of France?"})
print(result["answer"])

Both repositories aim to simplify working with AI models and prompts, but Promptflow offers a more structured approach with flow-based designs, while Continue focuses on a simpler, more direct interaction model. Promptflow may be better suited for larger, enterprise-scale projects, whereas Continue might be preferable for quick prototyping or smaller applications.