Cody
Codebase-aware AI coding assistant from Sourcegraph with chat, autocomplete, and inline edits powered by your full repository context.
Updated 2026-05-01
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.
What sets Cody apart
- Codebase-wide context via Sourcegraph's code intelligence engine
- Choice of Claude, GPT-4o, Gemini, or Mixtral per task
- Enterprise tier integrates Sourcegraph code search across multiple repos
- Works as a VS Code and JetBrains extension without switching editors
Key features
Codebase Context
Uses 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
- ✓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 capable 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 | Development teams who want an AI coding assistant that reasons over their entire codebase and multiple repositories, not just the open file. | Free tier + Pro $9/mo + Enterprise custom | 8.6/10 |
| Cursor vs Cursor → | Professional developers handling complex, multi-file refactors who want AI built into a familiar VS Code-based editor. | Freemium | 9.5/10 |
| GPT-5.5 vs GPT-5.5 → | Developers and teams needing a frontier reasoning model for agentic coding workflows and large-codebase context handling. | API: $5/$30 per 1M tokens (in/out). ChatGPT Plus $20/mo, Pro $200/mo | 9.4/10 |
| Windsurf vs Windsurf → | Developers who want an AI IDE that autonomously plans, codes, tests, and iterates across a project with minimal input. | Freemium | 9.1/10 |
Compare head-to-head
Related reading
Grok 4.6 Release Date: Two Weeks Out, Per Musk
Elon Musk put Grok 4.6 about two weeks out on July 28, with 4.7 close behind. What that timeline changes for anyone already building on Grok 4.5.
Two Settings Tripled GPT-5.6 Sol's ARC-AGI-3 Score
OpenAI says two Responses API settings took GPT-5.6 Sol from 13.3% to 38.3% on ARC-AGI-3's public set. Where that number holds, and where it doesn't.
OpenAI Codex Security CLI: Setup and the Catch
OpenAI open-sourced the Codex Security CLI on July 29. What it scans, what to check before wiring it into CI, and who is grading whose homework.
Ready to try Cody?
Head to the official site to start with Cody — pricing and plans are listed above.
Visit Cody