Skip to main content
Dundie·Feature Parity Map← all products

continue capabilities

12 mapped capabilities, each graded and dated. This is the diagnosis — the migration guide is the cure.


Capabilities

Autonomous agent mode

provisionalverified 2 days ago

An autonomous coding assistant that reads files, makes multi-file changes, runs terminal commands, and handles complex multi-step tasks from a single natural-language instruction. Before each tool use the agent requests approval by default; users click Continue to approve or Cancel to reject.

low confidence · 0.55docssource ↗source ↗

CLI and headless/background agents (cn)

provisionalverified 2 days ago

The Continue CLI (cn) runs the AI agent from the terminal in interactive TUI mode or non-interactive headless mode, enabling scripted automation, CI/CD integration, and background coding tasks without an IDE.

low confidence · 0.60docssource ↗source ↗

Context providers (@-mentions for chat context)

provisionalverified 2 days ago

In chat and agent mode, users type @ to attach specific context sources — files, terminal output, git diffs, and more — so the model has precise, relevant information without pasting manually.

low confidence · 0.55docssource ↗source ↗

Continue Hub / Mission Control (shareable assistants and blocks)

provisionalverified 2 days ago

Mission Control is Continue's cloud dashboard for creating, sharing, and running AI agents and reusable configuration blocks (models, rules, prompts, MCP servers). Teams compose and publish assistants that any team member can install with a single click.

low confidence · 0.60docssource ↗source ↗

Full model choice and BYOK (bring your own key)

provisionalverified 2 days ago

Users supply their own API keys for any supported model provider, or run models locally. There is no locked-in model — every provider and model is user-configurable via config.yaml.

low confidence · 0.55docssource ↗source ↗

IDE extension surfaces (VS Code and JetBrains)

provisionalverified 2 days ago

Continue ships as a native extension for Visual Studio Code and as a plugin for JetBrains IDEs. Both surfaces provide autocomplete, chat, inline edit, and agent mode within the editor.

low confidence · 0.60docssource ↗source ↗

In-editor AI chat

provisionalverified 2 days ago

An interactive AI assistant panel embedded in the IDE for asking questions, analyzing code, and getting guidance without leaving the editor. Supports three sub-modes: Chat (no tools), Plan Mode (read-only tools), and Agent Mode (full tool access).

low confidence · 0.55docssource ↗source ↗

Inline edit (targeted code modification)

provisionalverified 2 days ago

Select a code region, press Cmd/Ctrl+I, describe the change in natural language, and a diff is streamed inline. Designed for focused, single-function changes such as refactoring, adding comments, generating tests, or converting between languages.

low confidence · 0.55docssource ↗source ↗

Inline tab autocomplete

provisionalverified 2 days ago

Provides AI-powered inline code suggestions as you type, which you accept with Tab. Supports single-line and multi-line completions triggered automatically or manually.

low confidence · 0.55docssource ↗source ↗

MCP (Model Context Protocol) tool extension

provisionalverified 2 days ago

Continue supports the Model Context Protocol standard, allowing any MCP server to be added as a tool extension for the AI agent. This enables integration with external data sources, APIs, databases, and custom tooling.

low confidence · 0.55docssource ↗source ↗

Plan, pricing, and feature gating

provisionalverified 2 days ago

Continue's core IDE extension and CLI are free and open-source (Apache 2.0). Cloud/team features in Mission Control are gated behind paid tiers. Model costs are paid directly to whichever provider the user configures (BYOK).

low confidence · 0.60docssource ↗source ↗

Rules and custom prompts (slash commands)

provisionalverified 2 days ago

Rules are persistent instructions injected into the system message for every Agent, Chat, and Edit request. Prompts are reusable slash-command templates invoked with a / prefix for specific tasks.

low confidence · 0.55docssource ↗source ↗

Editorial guidance, not a warranty. AI tools change weekly; every entry carries the date it was last verified. Verify before relying on a specific capability.