Can Continue use Amazon Bedrock?
Yes. Continue documents a Bedrock provider configured with an AWS profile, access keys or a Bedrock API key.
Compare
Topsoil and Continue, compared fairly.
Continue is an open-source coding agent with a CLI and VS Code and JetBrains extensions, and it can be configured to use Amazon Bedrock. Topsoil is a commercial private AI coding agent built on Bedrock with a governed workflow.
The short version
Continue gives you an open-source, configurable agent you wire to the models you choose, Bedrock included. Topsoil adds an opinionated workflow on top of Bedrock: staged runs, a model per stage, tests that must fail first, budgets and a backlog-to-pull-request path.
| Topsoil | Continue | |
|---|---|---|
| Licence | Commercial product from Thazen | Open source, Apache 2.0 |
| Bedrock | Built on Bedrock: IAM, profiles, IAM Identity Center or Bedrock API keys | Configurable Bedrock provider with an AWS profile, access keys or a Bedrock API key |
| Surfaces | Terminal, VS Code bridge, desktop app, customer-hosted browser app | CLI, VS Code extension, JetBrains plugin |
| Workflow | Explore, design, plan, implement, verify, review, document, in an isolated worktree | Agent, chat, edit and autocomplete modes |
| Budgets | Monthly user and account budgets before each model call; AWS budget backstop | Through the provider you configure |
Facts about other products are taken from their public documentation, linked below. Products change; check the vendor’s current docs before deciding. If something here is out of date, tell us and we will correct it.
Which one fits
Where Continue is a strong fit
- You want an open-source agent you can read, fork and configure.
- You want JetBrains support or inline autocomplete.
Where Topsoil is a strong fit
- You want inference to stay in your own AWS account, on Amazon Bedrock, including AWS GovCloud (US).
- You want no vendor-operated service, prompt store or telemetry in the request path.
- You want a staged workflow (explore, design, plan, implement, verify, review, document) with a different Bedrock model per stage.
- You want monthly user and account budgets checked before each model call, with an AWS budget action as a backstop.
- Your backlog is GitHub Issues, or Jira Data Center with Bitbucket Data Center inside your own network.
The two are not mutually exclusive: teams sometimes run more than one tool for different work. Ask us about a pilot to compare on your own code.
Questions
Frequently asked questions.
See it against your own codebase.
A pilot runs in your own AWS account, with your models and your material, and ends with findings you can act on.