Continue is Cursor’s now. Your models still need an editor.
Continue was acquired by Cursor in 2026. Its repository is read-only and 2.0.0 was the final release. If you chose it because it was open source and ran on your own models, twinny is built for the same reasons and is still maintained: it talks to the same local servers, does the same three jobs, and adds a gateway for teams.
- 01
Install twinny from the Marketplace or Open VSX. With a local server running, it finds it at first start and sets up chat, autocomplete and embeddings from the models you have.
- 02
Copy the rest across from your Continue config: each model there becomes a twinny provider. A chat role is a chat provider, autocomplete is an autocomplete provider, embed is an embeddings provider. Same host, port and model name.
- 03
Put your rules in the system prompt template, build the workspace index if you used codebase search, and turn on agent mode if you used Continue’s agent.
The same jobs
Fill-in-the-middle autocomplete as you type, chat with @ mentions for files and symbols, inline edits shown as a diff, code review, commit messages, and an agent that reads, searches and edits files and runs commands, asking before each command unless you allow it.
The same servers
Ollama, LM Studio, llama.cpp, LiteLLM, Open WebUI or any OpenAI-compatible server, on your machine or another. Hosted APIs too, if you want them.
Shared config without a hub
Export the provider list as JSON and import it on another machine. For a team, twinny-server hands every developer a key and a policy from one place on your network.
One gateway for the team
twinny-server sits on the machine with the models and gives every developer a key, usage per person, policy and an admin page. Free for 5 developers, $15 a seat after that, 30-day trial.
- Does my Continue install stop working?
- Not on its own. But the repository is read-only, so it will get no more fixes, including for new versions of VS Code and of the model servers.
- Can twinny read my Continue config file?
- No. Set the providers up once in the Providers tab, then use export and import for the next machine.
- Does twinny support MCP?
- Yes, in agent mode. Name your MCP servers in the twinny.chatToolsMcpServers setting and their tools join the agent’s own, each call asking before it runs. Servers run on your machine over standard input and output; HTTP servers are not supported yet.
- Is there a JetBrains plugin?
- No. twinny is for VS Code and the editors that install from Open VSX, such as VSCodium.
Everything else is on the home page: features, the team gateway, security and pricing.