Continue vs Goose: pricing, features and which to choose

Continue is an open source coding agent project for editors, terminals, and pull requests. Founded by Ty Dunn and Nate Sesti, it launched in 2023 and entered Y Combinator’s Summer 2023 batch. It began with VS Code and JetBrains extensions, then added a command line interface and repository based agents. Continue’s homepage says it joined Cursor, while the open source codebase remains freely available. A June 2026 report described the hosted product as wound down, with users given until July 15, 2026 to export data. That change matters because Continue is no longer best understood as an independent vendor with a stable commercial roadmap. It is better viewed as an Apache 2.0 codebase and technology handoff for teams willing to manage configuration, providers, permissions, and ongoing operation themselves.

A typical workflow begins with installing the VS Code or JetBrains extension, choosing model providers, and assigning roles for chat, edit, apply, autocomplete, embeddings, and reranking. Developers can add repository rules, context providers, prompts, tools, and markdown agent files. The CLI runs an agent locally with a command such as cn --agent. GitHub Actions can discover agent files, run them in parallel, write job summaries, and create separate Check runs. Agents can read files and run commands, so the documented workflow recommends scoped GitHub permissions, secret based API keys, local testing, and review before enabling write actions. This makes Continue useful for teams that want repository controlled instructions and pull request checks, but less suitable for buyers seeking managed agents with little configuration or operational responsibility.

Continue offers more provider control than GitHub Copilot and keeps agent definitions close to repository code. Cursor is the closest commercial comparison and now owns Continue, while Claude Code is a stronger terminal first alternative with a more defined product identity. Gemini CLI offers another terminal workflow, and Goose targets configurable open source agents. Continue’s acquisition makes independent direction and hosted availability uncertain, and its agents can read files and run commands, requiring permission review and human checking. Pick Continue if Apache 2.0 code, local models, provider choice, repository based agents, and source controlled GitHub workflows matter more than a supported standalone subscription. Choose Cursor instead for a commercial integrated editor, or Claude Code for a clearer terminal first product with less emphasis on maintaining the surrounding codebase.

Goose is Block’s open source terminal AI agent for developers and technical teams. Launched on January 28, 2025, it began with software engineering work such as code migrations, dependency installation, test execution, and file changes, then expanded toward research, writing, automation, and data analysis. The project uses the Apache License 2.0, allowing commercial use, modification, and distribution subject to its terms. Goose runs on the user’s machine through desktop applications for macOS, Linux, and Windows, plus a terminal client and API. Users can edit files, execute commands, and run tests. The project is active, costs $0, and does not include model usage. Block reported that about 12 specialists built the original system over nine months.

A Goose session starts in the desktop app or CLI after the user selects a language model provider. Goose sends the request and tool descriptions to that model, executes returned tool calls, and sends results back for another turn. Built in and external MCP extensions can add shell commands, file operations, web access, memory, browser automation, and application specific actions. Users can save sessions, resume them across desktop and CLI, create reusable recipes, and connect remote MCP services. Permission modes include automatic execution, approval before actions, conversation without tools, and smart approval. Permissions can also be set for each extension with allow, deny, or approval behavior. Goose supports hosted providers and local Ollama models.

Goose fits developers automating code changes, tests, shell workflows, and repeatable MCP recipes, along with teams requiring Apache licensed software, local execution, provider choice, and configurable permissions. It is less suitable for people seeking a zero setup hosted coding assistant, teams unable to review commands and extension permissions, or users wanting one bill that includes model usage. Continue and Gemini CLI are closer terminal alternatives, while Claude Code and Cursor offer more managed coding experiences. Compared with Gemini CLI, Goose puts more emphasis on model independence, local deployment, desktop and CLI access, MCP extensions, and configurable autonomy. Choose Goose when those priorities matter more than bundled inference and simpler onboarding. Developers and technical teams wanting local, open source agentic coding should pick Goose.