Inline code autocomplete
Copilot-style suggestions while typing
// official site: continue.dev ↗
AI / LLM · PRO TIER
Continuepro
Continue is an open-source AI code assistant for VS Code and JetBrains IDEs — inline autocomplete, chat panel, edit mode, agent mode. Connect any LLM (Ollama for local, OpenAI / Anthropic for cloud). The Cursor / GitHub Copilot alternative that respects your privacy.
// What it is
A closer look.
Continue is an open-source AI code assistant for VS Code and JetBrains IDEs — inline autocomplete, chat panel, edit mode, agent mode. Connect any LLM (Ollama for local, OpenAI / Anthropic for cloud). The Cursor / GitHub Copilot alternative that respects your privacy.
This BluixApps install hosts the documentation + config landing page. The actual assistant runs in your IDE.
// Use cases
What it's for.
Concrete scenarios where teams pick Continue over the SaaS alternative.
Chat with codebase
RAG over your local repos
Edit mode
describe a change, Continue patches code
Agent mode
multi-step refactors
Self-hosted LLM coding
pair with Ollama, fully local
// Who it's for
Built for these teams.
If your team profile matches one of these, Continue is a strong fit out of the box.
Developers
rejecting GitHub Copilot's privacy model
Privacy-bound enterprises
with code residency requirements
Local LLM enthusiasts
using Ollama
Cost-conscious teams
rejecting per-seat AI coding subscriptions
Multi-LLM experimenters
comparing providers on real work
// Differentiators
Why teams pick Continue.
When evaluating self-hosted options for this category, here are the dimensions on which Continue consistently lands above the alternatives.
- ✓Apache 2.0 — fully open
- ✓Multi-IDE — VS Code + JetBrains (one config)
- ✓Multi-LLM — works with any provider via OpenAI-compatible API
- ✓Active development — frequent releases
- ✓Customizable — config-as-code via JSON
- ✓Hub for teams — shared config + prompts (paid Hub option)
// Integrations
Connects to.
The stack you'll plug Continue into — services, protocols, and adjacent apps in the BluixApps catalog.
◇
IDE extensions
VS Code (official), JetBrains (official)
◈
LLM providers
OpenAI, Anthropic, Ollama, Together, Groq, custom
◆
Autocomplete models
codestral, qwen2.5-coder, starcoder, deepseek-coder
▣
Embedding
for codebase RAG
▦
MCP
emerging Model Context Protocol support
▩
Custom slash commands
define team workflows
▼
Continue Hub
team workspace sync (paid)
// Adoption & deployment
Notable users & community
- 20k+ GitHub stars
- Active Discord with thousands of developers
- Backed by Continue Inc. with sustainable hub + enterprise tiers
- Featured in privacy-first AI coding stack guides
- Standard alternative to Copilot in self-hosted environments
What we ship
- nginx + static HTML at port 65530 — landing page with install + config docs
- Not a runtime service — just documentation
- Customizable at
/opt/continuedev/index.html - Pairs with Ollama on same BluixApps VPS for fully local AI coding
- HTTPS via Let's Encrypt reverse proxy
- No backup needed (static documentation)
// Tips & operations
Run it properly.
Operational guidance from running this in production — what to lock down, what surprises people.
// PERFORMANCE
IDE plugin
Continue runs in your editor, not as a server
// SECURITY
Pair with Ollama
local LLM + Continue = fully self-hosted AI coding
// OPERATIONS
Autocomplete model matters
qwen2.5-coder:7b is the current sweet spot
// RELIABILITY
Codebase indexing
Continue builds local embedding index (no upload)
// DEPLOYMENT
Config in ~/.continue/config.json
version control with your dotfiles
// SCALING
No central server
each dev's IDE is independent
1024
// min ram (MB)
4
// min disk (GB)
65530
// access port
http
// protocol
pro
// bluixapps tier
// Alternatives in AI / LLM
Compare with
Project resources
Official sitecontinue.dev ↗