Sourcegraph Cody AI
sourcegraph.com
AI coding assistant that enhances developer productivity with context-aware
Description
Take controlof your codebase · Give humans and agents complete context to understand, oversee, and evolve the world · A tidal wave of code is coming. Code is growing faster than teams can understand or control it. · Take back control with complete codebase context · Stripe makes their fleet of internal AI agents more effective with the Sourcegraph MCP server · Understand.Oversee.Evolve.
Sourcegraph Cody is an advanced AI coding assistant that leverages the power of large language models and Sourcegraph's code graph to provide context-aware assistance. It offers features like code autocomplete, chat-based code explanations, and custom commands for common coding tasks. Cody integrates seamlessly with popular IDEs and code hosts, using codebase-specific context to deliver more accurate and relevant suggestions, making developers more efficient in writing, understanding, and maintaining code.
Features
Context-aware code assistance, AI-powered chat, Code autocomplete, Custom commands, Codebase-specific search
Use cases
Answering code-related questions, Generating and explaining code, Debugging and fixing errors, Automating repetitive coding tasks, Onboarding new developers to a codebase
FAQ
Sourcegraph Cody AI is an AI-powered coding assistant designed to help developers write, understand, and fix code faster. It leverages the context of your entire codebase—across multiple files and repositories—using Sourcegraph's advanced code search and intelligence platform.
The main features of Cody AI include Developer Chat, which allows you to ask questions about your code, generate new code, or edit existing code with AI assistance. It also offers Code Completions & Edits, providing intelligent autocomplete suggestions and enabling bulk code edits. Cody provides Context-Aware Assistance by understanding your entire codebase, not just the open file, leading to more relevant and idiomatic code suggestions. Furthermore, it assists with Debugging to help identify and fix errors, offers Customizable Prompts for specific tasks like unit testing or documentation generation, and supports Agentic Development (Amp) for planning and executing multi-step, multi-file changes autonomously for complex tasks.
Cody uses Sourcegraph's code search and code graph technology to index and analyze your codebase. When invoked, it pulls context from the files open in your IDE, other files and repositories you specify, and recently closed tabs and other relevant code snippets. Cody then ranks the most relevant context and sends it to a large language model (LLM) to generate responses.
Cody is available for Visual Studio Code, JetBrains IDEs such as IntelliJ and PyCharm, Visual Studio, and as a Web app.
No, Cody is currently only available for Sourcegraph Enterprise users. It is not available for individual or non-enterprise users.
Cody offers enterprise-grade privacy and security features including self-hosting, which allows you to host Sourcegraph and Cody on your own infrastructure. You can also use Custom API Keys for language models to keep your code within your infrastructure. Data Controls enable configuration of data export, retention, and deletion policies to meet compliance requirements, and Granular Permissions allow administrators to control access to code, AI features, and administrative settings.
To set up Cody AI, you need to connect your repositories to Sourcegraph, then index your codebase for search. After that, configure Cody with your preferred language models, import shared prompts, and set up permissions. Finally, you can start using Cody in your IDE or web app.
The benefits of using Cody AI include increased productivity, as developers can save significant time on coding tasks. It also helps maintain consistency and quality across large teams, and provides context-aware suggestions by understanding your entire codebase, leading to more relevant and idiomatic code. Additionally, Cody is designed with enterprise-grade security and compliance in mind.
To troubleshoot issues with Cody AI, you should verify your codebase indexing and search configurations, check integration settings with your IDE, and ensure multi-file awareness is enabled. Additionally, review logs for any errors, and reach out to Sourcegraph support for further assistance.
Support options available for Cody AI include detailed documentation, community forums, direct enterprise support plans, and tutorials and troubleshooting guides.
Yes, Cody supports customization through shareable prompts for specific tasks, integrations with tools like Notion and Linear, and customizable workflows and prompts to automate repetitive coding functions.
Cody allows you to store logs and interaction data within your infrastructure, configure retention duration and data deletion policies, and ensure auditability and control over AI-generated outputs.
Specs
| Type | Agent |
| Section | Coding & development |
| Pricing | has a free tier (от $49/mo) |
| Platform | Web only |
| Systems | web |
| Who for | Enterprise |
| Site language | en |
| Rating | 0.00 (0 reviews) |
| Views | 207 575 |
| Launched | 2024-07-25 |
