Continue Guide

Continue is an open-source (Apache 2.0) tool that has evolved from a VS Code / JetBrains autocomplete extension into a broader source-controlled AI platform. In 2026 its flagship feature is markdown-authored AI checks that run in CI and surface as GitHub status indicators on pull requests, plus a cn CLI for local development.

The IDE extensions still exist; this page focuses on the CLI + CI surface because that's where Continue is strongest today.

Setup

# macOS / Linux — shell script
curl -fsSL https://continue.dev/install.sh | sh

# Windows — PowerShell
irm https://continue.dev/install.ps1 | iex

# Or via npm (requires Node 20+)
npm install -g @continuedev/cn

# Check
cn --version

IDE extensions: install Continue from the VS Code Marketplace or JetBrains Marketplace.

Source-controlled AI checks

The core pattern: AI review criteria are markdown files in your repo, not dashboard config. Add .continue/checks/ to your repo:

your-project/
├── .continue/
│   └── checks/
│       ├── api-design.md
│       ├── no-todos.md
│       └── test-coverage.md
└── src/

Example check:

---
name: no-todos
description: Block PRs that add new TODO/FIXME comments to production code
---

Review the diff. If it adds any new `// TODO` or `// FIXME` comments in files
under `src/` (excluding tests), fail the check with a message pointing to the
offending lines. Otherwise pass.

On each PR, Continue runs every check and posts pass/fail as a GitHub status with suggested fixes for failures. Checks are versioned with your code — reviewers see the exact criteria that ran.

cn CLI

cn is the command-line entry point for local development and CI:

# Run all checks in .continue/checks/ against the current diff
cn checks run

# Run a specific check
cn checks run --check no-todos

# Interactive chat mode
cn chat

# Model picker
cn chat --model claude-sonnet-4-6

Providers

Continue is model-agnostic. Supported via config: Anthropic, OpenAI, Google, Ollama, Groq, Mistral, and others. Configure via .continue/config.yaml (or config.json in older setups) with your API keys.

IDE features (when using the extension)

• Inline autocomplete — completes the next few lines as you type
• Chat panel — sidebar conversation with the model
• Agent edits — multi-file edits with approval
• Slash commands — custom commands defined in markdown
• Custom models — swap providers without reinstalling

First win

Add a minimal check to your repo:

mkdir -p .continue/checks
cat > .continue/checks/no-secrets.md <<'EOF'
---
name: no-secrets
description: Block PRs that add hardcoded API keys or tokens
---

Review the diff. If it introduces any hardcoded strings that look like API keys
(OpenAI sk-, Anthropic sk-ant-, GitHub ghp_, AWS AKIA, or generic base64
secrets >30 chars), fail the check with the offending file and line numbers.
EOF

git add .continue/
git commit -m "add no-secrets AI check"
git push

Enable the Continue GitHub App on your repo, open a PR — the check runs automatically.

Gotchas

• Check quality depends on prompt quality. A vague check produces noisy pass/fail. Write checks like you'd write a code-review rubric.
• Costs compound across PRs. Each check is one or more LLM calls per PR. A repo with many checks and many PRs can run up bills fast — use cheaper models (Haiku, Flash) for routine checks.
• cn vs IDE extension confusion. They share some config but aren't identical. If something works in one and not the other, check the docs for each.
• Model-agnostic ≠ model-equivalent. A check tuned on GPT-5 may behave differently on Claude Haiku. Test checks across the models you actually use.

Best for

• Teams that want AI-enforced conventions in CI without SaaS lock-in
• Open-source projects — Apache 2.0, self-hostable
• Teams already comfortable with GitHub PR workflow

Further reading

• Official docs: docs.continue.dev
• GitHub: continuedev/continue
• CI integration — broader patterns for AI in CI