Cody
Codebase-aware AI coding assistant from Sourcegraph with chat, autocomplete, and inline edits powered by your full repository context.
Overview
Cody is Sourcegraph's AI coding assistant, and its defining advantage comes from Sourcegraph's roots as a code search and intelligence platform. While most AI coding tools work with whatever files you have open, Cody can index and reason over your entire codebase — including dependencies, internal libraries, and even code across multiple repositories. This deep context awareness means its answers and suggestions reflect how your team actually writes code, not just generic patterns.
The tool supports multiple LLMs including Claude, GPT-4o, Gemini, and Mixtral, letting developers pick the right model for different tasks. Autocomplete runs locally for speed, while chat and inline commands tap into the full context engine for more complex queries like explaining unfamiliar code, generating unit tests, or documenting functions with accurate references to your project's patterns.
Cody works as a VS Code and JetBrains extension, fitting into existing workflows rather than requiring a new editor. For enterprise teams, the integration with Sourcegraph's code search means you can ask questions that span your organization's entire codebase — a capability no standalone AI editor can match.
Key features
Codebase Context
Leverages Sourcegraph's code intelligence to index your full repository and pull relevant context from across your entire codebase, not just open files.
Multi-model
Choose between Claude, GPT-4o, Gemini, and Mixtral. Different models for different tasks — fast autocomplete vs. deep reasoning for complex questions.
Autocomplete
Fast inline code completions that understand your project's patterns, types, and conventions. Runs locally for low latency.
Pricing
Free tier: Autocomplete, chat, and commands with usage limits
| Plan | Price | What's included |
|---|---|---|
| Free | Free | Autocomplete, chat, commands, community support |
| Pro | $9/mo | Unlimited autocomplete and chat, premium models, personalized responses |
| Enterprise | Custom | Multi-repo context, Sourcegraph code search integration, SSO, admin controls, SLA |
Autocomplete, chat, commands, community support
Unlimited autocomplete and chat, premium models, personalized responses
Multi-repo context, Sourcegraph code search integration, SSO, admin controls, SLA
Pros & cons
Pros
- ✓Best-in-class codebase context — understands your full repo, not just the open file
- ✓Multi-model support lets you pick the right LLM for each task
- ✓Works as a VS Code and JetBrains extension — no need to switch editors
- ✓Enterprise tier integrates with Sourcegraph code search across multiple repositories
Cons
- ×Context engine is most powerful on Enterprise tier — free users get limited repo-wide context
- ×Lacks the autonomous agent and multi-file editing capabilities of Cursor or Windsurf
- ×Autocomplete quality lags behind GitHub Copilot and Cursor in head-to-head comparisons
- ×Sourcegraph integration adds complexity to enterprise setup and onboarding
How it compares
| Tool | Best for | Pricing | Score |
|---|---|---|---|
| Cody | — | Free tier + Pro $9/mo + Enterprise custom | 8.6/10 |
| Cursor | — | Freemium | 9.5/10 |
| GitHub Copilot | — | From $10/mo | 9.3/10 |
| Windsurf | — | Freemium | 9.1/10 |