Stacks / AI chat
Easy
Continue + LiteLLM
IDE autocomplete and chat over your models. GitHub Copilot without the seat.
The problem
GitHub Copilot Pro is $10/month per developer, then Pro+ and Max climb the credit ladder. Continue is the OSS IDE extension; LiteLLM already sits in the ChatGPT stack and can serve the same keys.
Replaces
GitHub Copilot
Estimated SaaS saved
$1,200
per year, small team, before lock-in
Deploy on RailwayContinue runs in the editor. LiteLLM is the Railway piece (already a c17 stack). Point Continue at the LiteLLM OpenAI-compatible URL.
The stack
Cost table
| You stop paying | Typical / year | Self-host instead |
|---|---|---|
| GitHub Copilot Pro (10 seats) | $1,200 | Continue + LiteLLM + your keys |
Agent setup prompt
Replace GitHub Copilot with Continue pointed at LiteLLM. - Deploy LiteLLM (see the Open WebUI stack) or reuse that proxy. Continue config uses the OpenAI-compatible endpoint and your model name. - Document one working VS Code setup. You still pay tokens. You stop paying Copilot seats.
Also as markdown: /stacks/continue-copilot.md
FAQ
- Is this the ChatGPT Team stack?
- Same proxy (LiteLLM), different UI. Open WebUI is the chat window. Continue is the editor. One set of keys.