Cody by Sourcegraph
AgentAgent that writes code and answers your questions
Capabilities11 decomposed
codebase-aware chat with selective context injection
Medium confidenceMulti-turn conversational interface that maintains chat history and allows users to annotate prompts with `@` syntax to explicitly inject file references, symbol definitions, remote repository context, and non-code artifacts. Integrates with Sourcegraph's Advanced Search API to retrieve codebase patterns and APIs across the entire indexed codebase, enabling context-aware responses without requiring manual copy-paste of code snippets.
Integrates Sourcegraph's Advanced Search API to retrieve codebase context server-side before generating responses, avoiding the need to send entire codebases to external LLM APIs. Uses `@` annotation syntax for explicit context control, allowing developers to selectively inject files, symbols, and repositories into chat without manual copy-paste.
Provides codebase-wide context retrieval without uploading entire repositories to cloud LLM providers, and offers more granular context control than GitHub Copilot's implicit file-based context.
inline code completion with repository context
Medium confidenceGenerates code completions at the cursor position in supported IDEs by analyzing the current file, open repository context, and optionally the broader codebase via Sourcegraph's Search API. Completions respect local coding conventions and patterns indexed in the codebase, enabling suggestions that align with existing architecture and style.
Leverages Sourcegraph's indexed codebase to generate completions that align with existing patterns and conventions, rather than relying solely on training data. Integrates with multiple IDE platforms (VS Code, JetBrains, Visual Studio) with consistent context retrieval.
Provides codebase-aware completions without sending code to external APIs, and respects local conventions better than generic LLM-based completers like Copilot.
enterprise deployment with self-hosted or single-tenant cloud options
Medium confidenceSourcegraph Enterprise offers self-hosted or single-tenant cloud deployment options, providing organizations with full control over data, infrastructure, and model selection. Deployments support air-gapped environments, custom authentication (SAML, LDAP), and integration with internal code hosts. Includes admin controls for user management, audit logging, and feature configuration.
Offers self-hosted and single-tenant cloud deployment options with full data control, air-gapped environment support, and custom authentication integration. Provides admin controls for user management and audit logging.
Provides more deployment flexibility and data control than SaaS-only alternatives like GitHub Copilot, enabling compliance with strict data governance requirements.
cursor-triggered auto-edit with contextual code modification
Medium confidenceAutomatically proposes code changes based on cursor position and recent edits in the editor. Activates after at least one character edit and analyzes the surrounding code context to suggest refactorings, fixes, or completions. Changes are presented as diffs for user review before application, maintaining human control over modifications.
Triggers code suggestions based on cursor position and edit activity rather than explicit user prompts, reducing friction for passive assistance. Presents all changes as diffs for explicit user approval, maintaining transparency and control.
More passive and context-aware than explicit chat-based code generation, and provides diff-based review unlike inline completions that auto-apply.
error identification and fix suggestion with codebase context
Medium confidenceAnalyzes code for errors, bugs, and issues by examining the current file and optionally retrieving related patterns from the broader codebase via Sourcegraph's Search API. Suggests fixes with explanations and applies changes through the auto-edit or chat interface. Leverages codebase-wide patterns to recommend fixes that align with existing conventions.
Combines error detection with codebase-wide pattern retrieval to suggest fixes that align with existing conventions and architecture. Integrates with Sourcegraph's Search API to find similar patterns and usage across the codebase.
Provides context-aware debugging suggestions that respect codebase conventions, unlike generic LLM-based debugging that lacks codebase-specific knowledge.
customizable prompt templates and workflows
Medium confidenceAllows users to create and execute premade or custom prompt workflows that can be triggered from the IDE or chat interface. Workflows can chain multiple operations (e.g., analyze code, generate tests, suggest refactorings) and accept parameters for customization. Stored locally or in Sourcegraph instance for team reuse.
Enables creation of custom AI-assisted workflows that can be stored and reused across teams, reducing repetition of complex prompts. Integrates with Sourcegraph instance for team-wide workflow management.
Provides workflow customization and reuse capabilities that generic chat-based AI assistants lack, enabling teams to standardize AI-assisted processes.
multi-ide and multi-platform deployment with consistent context
Medium confidenceDeploys Cody as extensions across VS Code, JetBrains IDEs (IntelliJ, PyCharm, etc.), Visual Studio (experimental), and web-based Sourcegraph instances. All deployments maintain consistent context retrieval via the same Sourcegraph backend, ensuring identical behavior and codebase access across platforms. CLI interface available for command-line workflows.
Maintains consistent context retrieval and behavior across VS Code, JetBrains, Visual Studio, and web interfaces by routing all requests through the same Sourcegraph backend. Provides CLI interface for integration into automated workflows.
Offers broader IDE support than GitHub Copilot (which focuses on VS Code and JetBrains) and maintains consistent codebase context across all platforms.
repository context filtering and exclusion
Medium confidenceAllows users to exclude specific repositories from Cody's chat and autocomplete context retrieval. Filters are applied at the Sourcegraph instance level, preventing sensitive or irrelevant repositories from being retrieved during context injection. Useful for managing access control and reducing noise in large multi-repository environments.
Provides repository-level context filtering at the Sourcegraph instance level, allowing organizations to control which codebases Cody can access during context retrieval. Filters apply consistently across chat and autocomplete.
Offers more granular access control than generic LLM-based assistants, enabling organizations to enforce data governance policies.
data privacy and model training opt-out
Medium confidenceOn Sourcegraph.com, Cody collects prompts and responses for service improvement but explicitly does NOT use them to train or fine-tune models for individual users. Users can review privacy policies and understand data handling practices. Self-hosted Enterprise deployments offer full data control with no external model training.
Explicitly guarantees that prompts and responses on Sourcegraph.com are NOT used to train or fine-tune models for individual users, and offers self-hosted Enterprise deployments for full data control. Provides transparency about data collection practices.
Offers stronger privacy guarantees than GitHub Copilot (which uses code for model training) and provides self-hosted options for organizations requiring full data control.
code host integration with github and gitlab
Medium confidenceIntegrates with GitHub and GitLab to access repository metadata, pull request context, and code host-specific information. Enables Cody to provide context-aware suggestions based on PR descriptions, issue context, and code host workflows. Supports authentication via code host credentials for seamless access control.
Integrates with GitHub and GitLab to retrieve code host-specific context (PR descriptions, issue links, branch metadata) and incorporate it into Cody suggestions. Maintains consistent authentication across Sourcegraph and code host.
Provides code host-aware context that generic LLM assistants lack, enabling suggestions that respect PR and issue context.
sourcegraph search result integration and in-context assistance
Medium confidenceCody chat is accessible directly from Sourcegraph search results and file views, allowing developers to ask questions about search results without context-switching. Chat maintains context of the currently viewed search results or file, enabling questions like 'How is this function used across the codebase?' or 'What does this code pattern do?'
Embeds Cody chat directly in Sourcegraph search results and file views, allowing developers to ask questions about discovered code without context-switching. Maintains context of current search results or file.
Reduces friction compared to opening a separate chat tool, and provides search-result-aware context that generic chat assistants lack.
Capabilities are decomposed by AI analysis. Each maps to specific user intents and improves with match feedback.
Related Artifactssharing capabilities
Artifacts that share capabilities with Cody by Sourcegraph, ranked by overlap. Discovered automatically through the match graph.
Tabby Agent
Self-hosted AI coding agent with full privacy.
Codecomplete.ai
CodeComplete is developing an Enterprise-focused AI code assistant similar to Github Copilot....
Augment Code (Nightly)
Augment Code is the AI coding platform for VS Code, built for large, complex codebases. Powered by an industry-leading context engine, our Coding Agent understands your entire codebase — architecture, dependencies, and legacy code.
Continue
Open-source AI code assistant for VS Code/JetBrains — customizable models, context providers, and slash commands.
Superflex: AI Frontend Assistant, Figma to React/Vue/NextJS/Angular (Powered by GPT & Claude)
Transform Figma designs into production-ready code with Superflex, your AI-powered assistant in VSCode. Built on GPT & Claude, Superflex generates clean, reusable code in seconds, saving hours on frontend work while preserving your design standards and coding style.
GitHub Copilot
AI pair programmer for real-time code suggestions.
Best For
- ✓developers working in large, multi-file codebases who need context-aware code assistance
- ✓teams using Sourcegraph for code search and wanting integrated AI assistance
- ✓developers who want to avoid sending entire codebases to external LLM APIs
- ✓developers in large codebases who want completions that respect existing patterns
- ✓teams with strong code style guidelines who want AI suggestions to match conventions
- ✓developers using Sourcegraph for code search who want integrated completion
- ✓enterprises with strict data governance or compliance requirements
- ✓organizations in regulated industries (finance, healthcare, government)
Known Limitations
- ⚠Context is per-session only — no persistent memory across separate chat sessions
- ⚠Requires Sourcegraph instance (cloud or self-hosted) to be running and indexed
- ⚠Context window size not documented — may truncate large codebases or complex queries
- ⚠No explicit reasoning artifacts or chain-of-thought transparency in responses
- ⚠Scope of context retrieval not documented — unclear if completions use full codebase or limited window
- ⚠No configuration options documented for completion aggressiveness or filtering
Requirements
Input / Output
UnfragileRank
UnfragileRank is computed from adoption signals, documentation quality, ecosystem connectivity, match graph feedback, and freshness. No artifact can pay for a higher rank.
About
Agent that writes code and answers your questions
Categories
Alternatives to Cody by Sourcegraph
Are you the builder of Cody by Sourcegraph?
Claim this artifact to get a verified badge, access match analytics, see which intents users search for, and manage your listing.
Get the weekly brief
New tools, rising stars, and what's actually worth your time. No spam.
Data Sources
Looking for something else?
Search →