Sourcegraph Cody is an AI coding assistant that understands your entire codebase to answer questions, write patches and explain unfamiliar code.
Cody combines large language models with Sourcegraph’s code intelligence, so its answers are grounded in your actual repositories rather than generic training data. It indexes large codebases, resolves cross-repository dependencies and cites the files behind every answer. Cody works where developers already are: as extensions for VS Code, JetBrains and Neovim, and through a CLI for scripted use. Autocomplete, inline chat and command-based refactoring cover the daily loop from exploration to merge-ready diffs.
Cody has a free tier for individual developers, a Pro plan with higher model limits and enterprise pricing that adds admin controls, SSO and private model deployments.
It is aimed at professional developers working in large or legacy codebases where knowing “where things are used” matters as much as generating code. Platform teams standardizing AI tooling benefit from its admin features.
Install the extension for your editor, connect it to your organization’s code hosts and let Cody index the repositories you work with. Ask questions in chat โ where a function is used, how an error path behaves โ and Cody answers with citations you can open directly. Autocomplete runs as you type, and custom commands let teams standardize tasks like generating tests or summarizing pull requests.
Cody earns its keep in large or aging codebases where simply knowing where to look is half the battle. Define a few team commands early so AI output follows house conventions rather than drifting per developer. Platform teams should review indexing scope and model settings before rollout, since answer quality depends on the context Cody is allowed to see.
Yes, individuals can start on a free plan. Higher usage, advanced models and enterprise controls are paid.
Cody exposes a CLI and enterprise APIs alongside editor plugins, so it can be embedded in custom developer workflows.
Its edge over single-file assistants is deep codebase context and citations, which makes answers auditable and far more reliable in large repositories.
Cody ships as extensions for VS Code, JetBrains IDEs and Neovim, and is also available through a command-line interface. Teams with mixed editor preferences can standardize on the same assistant across the engineering organization.
Gemini CLI is Google's open-source AI coding agent that brings frontier Gemini models into the terminal with a remarkably generous free tier.OverviewLaunched…
OpenCode is an open-source, terminal-native coding agent that is model-agnostic, letting you run any LLM provider or local model against your repository.OverviewOpenCode…
Crush is Charm's glamorous open-source coding agent for the terminal, bringing multi-model AI assistance to a beautifully crafted command-line experience.OverviewCrush comes from…