continuedev/continue
Continue
Continue is an automated code review platform that integrates AI agents directly into the software development lifecycle. By executing custom validation rules against pull request diffs, it provides immediate feedback through repository status checks, allowing teams to enforce quality, security, and documentation standards before manual review begins.
The system distinguishes itself through a file-based configuration model where validation logic is defined in version-controlled markdown files. These files act as system prompts that guide autonomous agents in evaluating code changes. This approach enables agentic task chaining, where specialized workflows—such as security scanning, test coverage validation, and UI rendering verification—are orchestrated to analyze code against project-specific criteria.
Beyond automated reviews, the platform includes a local-first execution engine that allows developers to run and refine these checks from the command line before committing changes. The system also incorporates a feedback loop that tracks user acceptance and rejection of suggestions, enabling the refinement of check logic over time to reduce noise and improve the accuracy of automated findings.
The project provides a command-line interface for managing these workflows and integrates with repository webhooks to trigger analysis automatically upon pull request submission.
Features
- Agentic Workflows - Coordinates autonomous agents to execute specialized analysis workflows across the development lifecycle.
- Automated Code Review - Automates code reviews by running AI agents that verify quality and provide feedback directly in the repository.
- AI Orchestration - Manages the lifecycle of automated code analysis by chaining specialized agentic tasks.
- Prompt-Based Logic Engines - The system interprets markdown-based instructions as system prompts to guide large language models in evaluating code changes against defined criteria.
- Development Workflow Automation - Integrates specialized agents into the software development lifecycle to handle repetitive tasks.
- Vulnerability Scanners - Scans code changes for common security flaws and potential leaks to prevent vulnerabilities from being merged.
- Agentic Task Automation - Deploys specialized agents to automate tasks like security scanning and pipeline monitoring.
- AI Code Reviewers - Evaluates pull requests against custom logic and security patterns to maintain consistent software quality standards.
- Prompt Engineering Templates - Interprets markdown-based instructions as system prompts to guide language models in evaluating code.
- CI Integrations - Triggers automated validation logic immediately upon submission of pull request events.
- Webhook Integrations - Automated workflows are triggered by repository events to execute validation logic immediately upon the submission of new pull requests.
- Static Analysis - Audit code and refine logic by running custom checks against local branches or specific diffs before deploying them to the team.
- Agentic Coding Tools - Open-source coding agent for IDE integration.
- AI Coding Assistants - Open-source copilot chat for VS Code.
- AI & Machine Learning - Open-source AI coding assistant for IDEs.
- Client Applications - IDE extension providing autocomplete and chat capabilities with MCP support.
- Extensions and Plugins - Build your own in-editor AI agents using plugins and rules.
- AI Coding Assistants - Open-source autopilot for VS Code development tasks.
- Client Applications - Open-source AI coding assistant that supports MCP servers.
- Coding Agents - Open-source AI code assistant for IDEs.
- Coding Agents and IDEs - Modular AI extension for VS Code and JetBrains.
- Developer Tools - Open-source IDE assistant for custom autocomplete and chat.
- Development Environments - Open-source AI code assistant for VS Code and JetBrains.
- Plugins and Extensions - Open-source agent with IDE extensions and source-controlled AI checks for CI.
- AI - Listed in the “AI实用编程工具” section of the DotNetGuide awesome list.
- Command Line Interfaces - Provides a command-line interface to manage and execute AI-powered code checks.
- Local Development Tools - Provides a command-line interface to iterate on automated checks locally before committing to the pipeline.
- CI/CD Integrations - Link a repository to the service to trigger automated code analysis whenever new pull requests are submitted to the selected project.
- Code Quality Tools - Executes defined validation rules and testing criteria directly within the development lifecycle for every code change.
- Configuration as Code - Stores custom validation logic in version-controlled files to ensure configurations evolve with the source code.
- Continuous Integration Validators - Enforces project-specific standards by running automated checks against code diffs before manual review occurs.
- Pull Request Review Tools - Enables review and application of suggested code improvements directly from status checks.
- Code Coverage Tools - Validates that new code includes corresponding tests by checking naming and structural conventions.
- Linters & Formatters - Enables the creation of custom quality criteria using markdown-based metadata and instructions.
- Schema Validation Tools - Create markdown files in a designated directory to define custom validation rules that the system executes against every pull request diff.
- Visual Regression Testing - Uses browser-based testing to ensure modified pages render correctly and adhere to design standards.
- Automated Check Generation - Uses automated agents to generate and configure custom checks based on project context.
- Development Agents - Automates repetitive tasks like security scanning, documentation verification, and performance monitoring across software repositories.
- Model Feedback Loops - Refines automated check logic by tracking user acceptance and rejection of suggestions.
- Documentation Management - Flags pull requests where modifications to interfaces lack corresponding updates to project documentation.
- Agent Performance Monitoring - Tracks execution frequency and operational costs to evaluate the effectiveness of automated workflows.
