How does Cody get context about my code?

Cody uses Sourcegraph's advanced Search API to pull context from both your local editor and remote repositories, including files, symbols, and usage patterns across your entire indexed codebase.

Is my code used to train AI models?

For Enterprise customers, Sourcegraph does not use your code to train shared models. Fine-tuning can be enabled by an admin to customize a model exclusively for your use. Individual users' data is not used for training.

What are Sourcegraph credits and how are they used?

Credits are the currency for AI features within Cody Enterprise. They are included in your contract based on team size and can be pooled org-wide. They expire on renewal unless purchased as a volume bucket add-on.

Can I self-host Sourcegraph and Cody?

Yes. Sourcegraph offers an Enterprise self-hosted deployment option. You can run the entire platform, including Cody, on your own infrastructure for greater control and security.

How is a 'billable active user' counted for Cody?

A user is counted as active and billable when they are signed into their Enterprise account and actively interact with Cody (e.g., see autocompletions, run commands, chat). Mere installation is not enough.

Does Cody work with GitHub Copilot or other AI tools?

Yes. The Sourcegraph platform, including its MCP server and APIs, is designed to provide context to other AI coding agents like Claude Code, Cursor, and Codex, enhancing their effectiveness.

Directory/Coding/AI Assistants/Cody

Cody

Cody is Sourcegraph's AI-powered coding assistant designed to help developers understand, write, and fix code faster. It integrates with popular IDEs like VS Code, JetBrains, and Visual Studio, as well as the Sourcegraph web app. Its core capability is leveraging large language models (LLMs) alongside a deep understanding of your entire codebase, pulled via Sourcegraph's advanced Search API. This provides context-aware chat, code completions, auto-edits, and customizable prompts that reference APIs, symbols, and usage patterns across your local and remote repositories. Targeted at professional software developers and engineering teams, Cody aims to boost productivity by acting as a context-aware pair programmer that can debug code, automate workflows, and seamlessly integrate with existing tools and code hosts like GitHub and GitLab.

Coding

Visit website

Added on

Sep 16, 2026

AI Coding AssistantMulti-repo ContextEnterprise SearchBatch ChangesCode InsightsIDE ExtensionsSelf-hosted Option

Product information

Everything worth knowing about Cody

The complete picture — from everyday features to the technical detail builders and IT folks dig for.

Core features

What it actually does

AI Chat with Context

Chat directly with AI models to ask questions about your code, generate code, and edit code. Cody uses your open file and repository context by default, and you can use @ to add context from specific files, symbols, or remote repositories.

Auto-Edit Suggestions

Suggests code changes by analyzing cursor movements and typing, proposing contextual modifications based on your recent edits and position.

Customizable Prompts

Automate key tasks with premade and customizable prompts, saving and sharing common queries with your team.

Deep Code Context

Uses Sourcegraph's advanced Search API to pull context from both local and remote codebases for accurate, codebase-aware results.

Debugging Assistance

Optimized to identify and fix errors in your code, accelerating the debugging process.

Context Filtering

Ignore selected repositories from chat and autocomplete results to control what context your codebase uses.

Technical capabilities

Multi-IDE and Codehost Integration

Seamlessly connects with code hosts (GitHub, GitLab) and IDEs (VS Code, JetBrains, Visual Studio).

Must watch videos

Sourcegraph Cody for AI Codebase Assistant Honest Review - Watch Before Using

2:19

Review2:19

Sourcegraph Cody for AI Codebase Assistant Honest Review - Watch Before Using

This video is about: ▶Sourcegraph Cody for AI Codebase Assistant Honest Review - Watch Before Using Links to other usefull products: Shopify - https://shopify.pxf.io/y2dy6b VPN by SurfShark - https://surfshark.sjv.io/Y96LVr ESim by MayaMobile - https://mayamobile.pxf.io/VONQq6 Stock Vids&Photos by Envato - https://1.envato.market/MAXkqP Hope it was helpfull. Subscribe and Like!

Sourcegraph Cody Review Best AI Coding Assistant Tested

2:28

Review2:28

Sourcegraph Cody Review Best AI Coding Assistant Tested

This video teaches you how to effectively use Sourcegraph Cody, one of the best AI coding assistants available today. We provide an in-depth review covering its key features, usability, and performance in real-world coding scenarios. Learn how Cody can help you write code faster, debug smarter, and improve your overall development workflow. Whether you are a beginner or an experienced developer, this review will help you decide if Sourcegraph Cody is the right tool for your coding needs. Watch as we test its capabilities and compare it to other AI coding assistants. Welcome to Twiz27! Got a question or need more help? Leave a comment below. Subscribe for more step-by-step tutorials: https://www.youtube.com/@twiz27

Cody: the AI assistant that actually knows your codebase

10:06

Tutorial10:06

Cody: the AI assistant that actually knows your codebase

Check out Cody at https://sourcegraph.com/cody?utm_source=social&utm_medium=social&utm_campaign=cody_ga_aaron. I tried Cody across a couple of different codebases and was super pleased with the way that the context worked. It felt like it actually understood my projects moreso than any of the other assistants. Thank you to SourceGraph for supporting the channel! Follow me: Twitter: https://twitter.com/aarondfrancis LinkedIn: https://www.linkedin.com/in/aarondfrancis Website: https://aaronfrancis.com - find articles, podcasts, courses, and more. Chapters: 00:00 Who is Cody? 00:41 Trying it on the Laravel framework 02:25 How do I add a scope? 04:52 Trying it on an obscure repo 06:41 Using Cody to fix our code 07:28 Code generation 08:55 Cody is GA, with a few rough edges

Who uses it

Real use cases, no hype

Enterprise Codebase Navigation

Navigate and understand massive, multi-repo codebases with jump-to-definition and find references across any branch or commit.

AI-Powered Code Generation

Use Cody's chat and completions to write boilerplate, generate functions, and refactor code with full codebase context.

Large-Scale Refactoring & Migrations

Plan and execute automated, tracked changes across hundreds of repositories using Batch Changes and Agentic Batch Changes.

Code Security & Vulnerability Management

Identify and remediate security vulnerabilities at scale with Code Insights and monitoring across your entire codebase.

Developer Onboarding & Knowledge Transfer

Accelerate onboarding by allowing new developers to ask natural language questions about code architecture and patterns.

Codebase Analytics & Metrics

Track usage patterns, code health, migration progress, and technical debt with customizable Code Insights dashboards.

AI Agent Context Provision

Provide other AI coding agents (Claude Code, Cursor, Codex) with deep codebase context via the MCP server and APIs.

What's great

Powerful chat with customizable @-mentions for files, symbols, and repos
Seamless IDE integration (VS Code, JetBrains, Visual Studio, Web)
Agentic capabilities for large-scale batch changes and code migrations
Integrated with Sourcegraph's broader Code Intelligence platform (Search, Insights, etc.)

Technical strengths

Deep codebase context via advanced Search API across local and remote repos
Context-aware auto-edits and completions based on cursor position and recent changes
Enterprise-grade security with single-tenant cloud or self-hosted options

Where it falls short

High entry price: $16K minimum annual contract
Requires Sourcegraph Enterprise for full functionality
Credit-based AI feature billing can be complex and unpredictable
Limited to supported languages and code hosts; not universal

Technical limitations

Context gathering relies on Sourcegraph's indexing, which can be slow for large monorepos
Potential vendor lock-in with the Sourcegraph ecosystem and proprietary APIs
Performance of agentic features (e.g., Batch Changes) depends on codebase size and complexity

For technical folks

The deep-dive specs

Deployment Options

Single-tenant cloud, Self-hosted

AI Model Provider

Sourcegraph Model Provider

Integrations

GitHub, GitLab, VS Code, JetBrains, Visual Studio, CLI, MCP Server, GraphQL and REST APIs

FAQ

Includes technical Q&A

Cody is an AI coding assistant that uses LLMs and your codebase context (via Sourcegraph's Search API) to help you understand, write, and fix code. It integrates into your IDE and connects to remote code repos.