Continue
Open-source AI code assistant VS Code and JetBrains extension — autocomplete, chat, and edit with any LLM.
Continue
Continue is the leading open-source AI code assistant for VS Code and JetBrains IDEs. It connects your editor to any LLM — cloud or local — providing inline autocomplete, a chat sidebar, and block editing commands, all configurable through a single config.json.
Key Features
- Tab autocomplete powered by FIM models (DeepSeek, Starcoder2, Codestral)
- Chat with full codebase context via
@codebase,@file,@git-diffmentions - Edit mode: select code, describe the change, apply instantly
- Connect to Claude, GPT-4, Gemini, Mistral, Ollama, LM Studio, or any OpenAI-compatible endpoint
- MCP integration: use any MCP server as a context provider or tool inside the IDE
Quick Start
# Install from VS Code Marketplace
code --install-extension Continue.continue
# Or JetBrains Marketplace: search "Continue"
Configure ~/.continue/config.json:
{
"models": [{
"title": "Claude Sonnet",
"provider": "anthropic",
"model": "claude-sonnet-4-5"
}],
"tabAutocompleteModel": {
"title": "Codestral",
"provider": "mistral",
"model": "codestral-latest"
}
}
npx ai-supply add continue-dev-ai-codebase
Curated mirror of the open-source Continue (Apache-2.0). Get it from the source.
Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.
Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).
The same gate an agent runs before installing (POST /api/v1/trust/continue-dev-ai-codebase/check). Click a policy:
Consume Continue programmatically. Authenticate with an API key or session — see Authorize an agent.
# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/continue-dev-ai-codebase
# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/continue-dev-ai-codebase/check \
-H "Content-Type: application/json" \
-d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'
# CLI
npx ai-supply add continue-dev-ai-codebase
# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/continue-dev-ai-codebase/install \
-H "Authorization: Bearer $AIM_KEY"
# MCP tool
install_listing({ "slug": "continue-dev-ai-codebase" })OpenAPI spec →Curated mirror — latest upstream source. See the repository for tagged releases.