openagent @ continue ~ $

cat README.md

Continue

Open-source AI code agent for VS Code and JetBrains that combines chat, edit, agent, and autocomplete modes with source-controlled AI checks enforceable in CI.

# 32K Stars · 1.6K Forks · Apache-2.0 License // verified 2026-06-04
continue/main
$npm i -g @continuedev/cli
Installing Continue...
Continue ready
$continue --help
Reading continue configuration & environment...
# core strengths

What makes Continue different

Multi-mode workflow

Four integrated modes: Chat for questions, Edit for targeted changes, Agent for autonomous tasks, and Autocomplete for inline suggestions.

One extension covers the full spectrum of AI-assisted development, from quick completions to complex multi-file agentic tasks.

VS Code + JetBrains support

The only open-source coding agent with full feature parity across both VS Code and JetBrains IDEs.

Teams using different IDEs can standardize on one tool, and developers switching editors don't lose functionality.

CI-enforceable AI checks

Source-controlled AI checks defined as markdown files in your repository, running as GitHub status checks on every PR.

Makes AI-assisted development auditable and governed by version control — the same workflow as traditional CI/CD checks.

Model-agnostic architecture

Supports any LLM provider through an extensible model system, including local models via Ollama.

Teams can choose the best model for each task without being locked into a single provider.
# quick start

Your first command

terminal
$npm i -g @continuedev/cli
# use cases

How developers use Continue

01

Automated code review in CI

Define AI review checks as markdown files in .continue/checks/ — every PR gets automated security, style, and correctness review.

02

Mixed-mode development

Use Autocomplete for quick suggestions, switch to Agent for complex tasks, and use Chat for architectural questions — all in one session.

03

Cross-IDE team workflows

Some team members use VS Code, others use JetBrains — Continue provides the same AI coding capabilities in both editors.

# comparison

How Continue compares

Choose Continue for multi-IDE support and CI checks vs Cline

Continue supports both VS Code and JetBrains with CI-enforceable AI checks. Cline has deeper autonomous agent capabilities but is VS Code-focused.

# faq

Questions

Q: What should I check before using Continue?

Start with one safe workflow for Continue. Inspect official setup instructions, required credentials, execution logs, approval points, and failure recovery before expanding from a sandbox task into production automation.

Q: Is Continue open source?

Continue is listed with Apache-2.0 based on the official source links in this profile. Re-check the repository, model card, or docs before production use.

Q: What IDEs does Continue support?

Continue supports both VS Code and JetBrains IDEs with full feature parity across chat, edit, agent, and autocomplete modes.

Decision brief

Should you use Continue?

JSON
Best for
  • Developers who need both VS Code and JetBrains support
  • Teams that want AI checks enforced in CI pipelines alongside agentic coding
  • Engineers who want a single tool covering chat, edit, agent, and autocomplete workflows
Not for
  • Users who prefer terminal-native agents over IDE extensions
  • Teams looking for a standalone coding agent without IDE integration
Trust and freshness
  • Verified 2026-06-04
  • License: Apache-2.0
  • Repo: continuedev/continue
  • Open-source signal
Deployment

cloud

Permission surface

shell/files

Decision signals

No extra signals recorded

Agent packet

Structured decision data for Continue

This packet is the compact machine-readable view agents should use before following source links or taking action.

Capabilities

workflow orchestration

Constraints

open source

Deployment

cloud

Permission surface

shell/files

Recommended workflows

Coding agent workflow

Overview

What Continue does

What it is

Continue is an open-source AI code agent for VS Code and JetBrains with four modes — Chat, Edit, Agent, and Autocomplete — plus source-controlled AI checks that run as GitHub status checks in CI pipelines.

Why it matters

Most coding agents operate only in the development environment. Continue's CI check system extends AI assistance into the pull request workflow, making it auditable, version-controlled, and enforceable — bridging the gap between AI-assisted development and traditional software engineering governance.

How to evaluate it

Start with one safe workflow for Continue. Inspect official setup instructions, required credentials, execution logs, approval points, and failure recovery before expanding from a sandbox task into production automation.

Facts

Known metadata and operating surface

These fields are separated from editorial interpretation so agents can reason over facts and missing checks.

Resource type agent
Category Agents
Maturity active
Difficulty Unknown
License Apache-2.0
Pricing open source
Verified 2026-06-04
Source confidence high
Risk level moderate
Fit matrix

Where Continue fits in an agent stack

strong

Coding agent workflow

Continue has multiple signals for coding agent workflow, including matching tags, capabilities, category, or positioning.

  • Run a small repository change and inspect the diff, tests, and rollback path.
  • Confirm official docs, current maintenance, license, and runtime constraints before production use.
partial

Connector or protocol layer

Continue has at least one signal for connector or protocol layer, but should be checked against a real task before adoption.

  • Connect one low-risk service, then inspect schemas, auth scope, errors, and logs.
  • Confirm official docs, current maintenance, license, and runtime constraints before production use.
partial

Reusable skill workflow

Continue has at least one signal for reusable skill workflow, but should be checked against a real task before adoption.

  • Run one skill end to end and check whether it produces evidence or structured output.
  • Confirm official docs, current maintenance, license, and runtime constraints before production use.
weak

Browser automation

Continue is not primarily positioned for browser automation in the current metadata.

  • Run one non-sensitive website task and inspect clicks, waits, retries, and changed URLs.
  • Confirm official docs, current maintenance, license, and runtime constraints before production use.
weak

Evaluation and observability

Continue is not primarily positioned for evaluation and observability in the current metadata.

  • Add one repeatable test case and confirm results can run again in review or CI.
  • Confirm official docs, current maintenance, license, and runtime constraints before production use.
weak

Local or private AI stack

Continue is not primarily positioned for local or private ai stack in the current metadata.

  • Verify hardware requirements, data path, storage, and whether all calls stay in your environment.
  • Confirm official docs, current maintenance, license, and runtime constraints before production use.
Inputs and outputs

What an agent should inspect

Likely inputs

  • Repositories, files, issues, terminal output, and test results
  • Prompts, messages, documents, images, or model inputs
  • Official setup instructions and a small real workflow

Likely outputs

  • Diffs, commits, explanations, test results, or review notes
  • A decision on whether this resource fits the target workflow
Evidence

Sources, claims, and missing checks

Claims are marked separately from source links so future crawlers and reviewers can update them without rewriting the page.

verified

Continue is listed as open source.

License metadata: Apache-2.0
verified

Continue has a recorded GitHub repository: continuedev/continue.

Resource facts and GitHub source link.
inferred

Continue supports these recorded deployment modes: cloud.

OpenAgent decision signal metadata.
inferred

Continue is tagged with workflow orchestration capabilities.

OpenAgent capability taxonomy.
Missing checks
  • Repository freshness has not been recorded.
Next action

How to start evaluating Continue

Inspect repository

Check license, recent activity, issues, examples, and security-sensitive code paths.

Open source

Open Homepage

Start from the official source before adopting third-party instructions.

Open source

Read setup docs

Use docs as the source of truth for installation and supported interfaces.

Open source

Install Continue CLI

Install the Continue CLI globally via npm, then run 'cn' in any project directory.

npm i -g @continuedev/cli
Compare

Alternatives and nearby resources

Use related resources to compare category fit, license, deployment model, and first-workflow behavior.

FAQ

Common questions about Continue

What should I check before using Continue?

Start with one safe workflow for Continue. Inspect official setup instructions, required credentials, execution logs, approval points, and failure recovery before expanding from a sandbox task into production automation.

Is Continue open source?

Continue is listed with Apache-2.0 based on the official source links in this profile. Re-check the repository, model card, or docs before production use.

What IDEs does Continue support?

Continue supports both VS Code and JetBrains IDEs with full feature parity across chat, edit, agent, and autocomplete modes.