Continue (software)

Continue is an open-source AI code assistant that integrates directly into code editors, letting developers connect any large language model (LLM) and customize AI-powered coding features including autocomplete, chat, code editing, and autonomous agent workflows. Developed by Continue Dev, Inc. and released under the Apache 2.0 license, Continue ships open-source extensions for Visual Studio Code and JetBrains IDEs and is model-agnostic, meaning teams bring their own model: they can connect cloud APIs or run models locally so code never leaves their machines ^[1][2][3]. The project accumulated over 34,000 stars on GitHub and more than 2.4 million installs on the Visual Studio Marketplace, and in June 2026 the company was acquired by Cursor maker Anysphere, after which the open-source repository was made read-only following a final 2.0.0 release while remaining under the Apache 2.0 license ^{[1][2][18][19]}.

Unlike proprietary competitors such as GitHub Copilot and Cursor, Continue gives developers full control over which models they use and where those models run. Users can connect to cloud-hosted APIs from providers like OpenAI, Anthropic, and Google, or run models locally using tools like Ollama and llama.cpp, keeping code entirely on their own machines ^[3].

What is Continue?

Continue is a developer tool that adds AI coding assistance (autocomplete, conversational chat, inline edits, and an autonomous agent) to existing IDEs through open-source extensions, rather than shipping its own editor. Its defining characteristics are that it is open source under the Apache 2.0 license and model-agnostic: the same interface works with dozens of cloud and local model providers behind a provider abstraction layer, so developers are not locked into a single AI vendor ^[2][3]. Continue described itself in its GitHub repository as a "Pioneering open-source coding agent" ^[2]. Co-founder and CEO Ty Dunn framed the project's philosophy around augmentation rather than automation: "If your intention is to be more productive, AI will amplify your productivity" ^[5].

History

When was Continue founded?

Continue was co-founded in June 2023 by Ty Dunn (CEO) and Nate Sesti (CTO) in San Francisco, California ^[4].

Ty Dunn studied Cognitive Science with a focus on Computer Science at the University of Michigan, graduating in 2019. After college, he joined Rasa, the open-source machine learning framework for building conversational AI, where he rose from the company's first product manager to Group Product Manager. At Rasa, Dunn oversaw a product with millions of downloads, 17,000 GitHub stars, and adoption by roughly 10% of the Fortune 500. In 2021, while at Rasa, Dunn began experimenting with GPT-3 for user simulation and OpenAI Codex for code generation, which planted the seed for Continue ^[5].

Nate Sesti studied mathematics and physics at MIT, where he also published research on graph neural networks. Before co-founding Continue, Sesti built mission control software at NASA's Jet Propulsion Laboratory (JPL) and served as the first engineer at Mayan, a Y Combinator Winter 2021 startup. His experience at NASA, where strict security policies prevented the use of LLMs on proprietary code, directly informed Continue's emphasis on local model support and data privacy ^[5].

Y Combinator and early growth

Continue was accepted into Y Combinator's Summer 2023 batch (S23). After graduating from YC in late 2023, the company raised $2.1 million in its first funding round, led by Jesse Robbins at Heavybit. Angel investors in this round included Julien Chaumond (co-founder of Hugging Face), Lisha Li (founder of Rosebud AI), and Florian Leibert (co-founder of Mesosphere) ^[4][6].

Version 1.0 and the Continue Hub

On February 26, 2025, Continue announced the release of version 1.0 alongside a new $3 million funding round in SAFEs (Simple Agreements for Future Equity), also led by Heavybit. This brought the company's total funding to approximately $5.1 million ^[6][7].

The v1.0 release introduced the Continue Hub (later renamed Mission Control), a platform for creating, sharing, and distributing custom AI coding assistants. The Hub functions as a registry where developers and organizations can publish and discover reusable building blocks: model configurations, rules, MCP servers, and complete assistant definitions. Continue compared the Hub to platforms like Docker Hub and the Hugging Face model registry ^[7]. Announcing the release, Dunn said: "With Continue 1.0, we are enabling this culture of contribution for developers to create and share custom AI code assistants" ^[5].

At the time of the v1.0 launch, Continue reported over 20,000 GitHub stars, more than 10,000 Discord community members, and hundreds of thousands of active users. Early enterprise customers included Siemens, Morningstar, and IONOS ^[7].

Continued development (2025-2026)

By March 2026, the GitHub repository had grown to over 32,000 stars with more than 21,000 commits, 4,300 forks, and 809 releases. The VS Code extension had surpassed 2.4 million installs, with version 1.3.34 as a release at that time ^[1][2]. The repository continued to grow, passing 34,000 stars and roughly 4,900 forks by mid-2026 ^[2]. The team remained small, with approximately five employees as of 2026 ^[4].

The product's focus expanded beyond IDE extensions to include the Continue CLI (cn), a command-line tool for running AI-powered code checks on pull requests as part of CI/CD pipelines. This positioned Continue not only as a developer tool but also as a quality control system for software teams ^[8].

What happened to Continue? (Cursor acquisition)

On June 18, 2026, Continue was acquired by Anysphere, the company behind the AI code editor Cursor. The acquisition was reported by outlets including The New Stack (published June 22, 2026) and Web Developer, both noting that the deal terms were not disclosed and that there was little formal announcement ^[18][19]. According to that reporting, "Continue's standalone product path ends, but its ideas and contributors move into Cursor's commercial stack" ^[19].

Around the acquisition, the Continue team shipped a final 2.0.0 release of the VS Code extension, CLI, and JetBrains plugin (the v2.0.0-vscode tag is dated June 19, 2026), which removed anonymous telemetry and authentication and fixed outstanding bugs. The continuedev/continue repository on GitHub was then made read-only, with a notice stating it "is no longer actively maintained and is read-only for all users." The codebase remained under the Apache 2.0 license (copyright 2023-2026 Continue Dev, Inc.), which matters for teams that had forked, vendored, or built internal tooling on top of Continue's architecture ^[2][18][19].

The acquisition occurred within a larger transaction: on June 16, 2026, SpaceX agreed to acquire Anysphere in a roughly $60 billion all-stock deal, widely described as the largest acquisition of a venture-backed startup, with the transaction expected to close in the third quarter of 2026 ^[20]. Reporting characterized Cursor's purchase of Continue as part of this period of consolidation in the AI coding tools market ^[18][19].

Architecture

Continue is built as a monorepo. As of early 2026, the repository's language composition was reported as follows ^[2]:

Scroll sideways for more →

The TypeScript core handles the shared logic for model interaction, context gathering, and tool orchestration. Kotlin is used for the JetBrains plugin, while Python and Rust handle specialized backend tasks. The extension communicates with LLMs through a provider abstraction layer, allowing the same interface to work with dozens of different model APIs and local inference engines ^[2].

What can Continue do?

Continue offers four primary interaction modes, each designed for different development tasks ^[9].

Chat

Chat mode provides a conversational interface within the IDE sidebar. Developers can ask questions about their codebase, request explanations of code, get debugging help, and discuss implementation approaches. In Chat mode, the AI operates without any tools; it functions as a knowledgeable conversation partner that can reference code context but cannot modify files ^[9].

Users can attach context to their chat messages using the @ symbol to reference specific files, functions, documentation sites, URLs, terminal output, and more ^[10].

Agent

Agent mode gives the AI model access to a full set of tools for autonomous coding tasks. When a developer describes a task in natural language, the agent can read and write files, run terminal commands, search the codebase, and make multi-file edits to complete the request. By default, the agent asks for permission before executing each tool, though users can configure automatic approval for specific tools ^[9].

Agent mode can be activated by pressing Cmd/Ctrl + . to cycle between Chat, Plan, and Agent modes. Plan mode serves as an intermediate option that gives the AI read-only tools for exploring the codebase and formulating a strategy without making changes ^[9].

Edit

Edit mode allows targeted, inline code modifications. A developer highlights a block of code, presses Cmd/Ctrl + I, and describes the desired change in natural language. The AI generates a diff that appears inline within the file, which the developer can accept or reject on a change-by-change basis using keyboard shortcuts ^[11].

Common use cases for Edit mode include refactoring functions, adding documentation comments, fixing bugs in specific code blocks, converting code between programming languages, and updating function signatures ^[11].

Autocomplete

Autocomplete provides inline code suggestions as the developer types, similar to the tab-completion experience offered by GitHub Copilot. Continue's autocomplete system uses a fill-in-the-middle (FIM) approach: the model receives the code before and after the cursor position and predicts what belongs in between ^[12].

The autocomplete pipeline consists of three phases: context gathering (collecting relevant code from open files and language server data), LLM inference (generating the completion), and rendering (displaying the suggestion inline). Developers can accept a full suggestion with Tab or accept word-by-word with Cmd/Ctrl + Right Arrow ^[12].

Autocomplete works best with models specifically trained for FIM tasks. Recommended models include Codestral (from Mistral AI), StarCoder, and Qwen Coder. Even relatively small models (3 billion parameters) can deliver strong autocomplete performance, while larger chat-oriented models often perform poorly in this role despite their general capabilities ^[12].

Which models and providers does Continue support?

Continue is model-agnostic. Rather than being tied to a single AI provider, it supports a wide range of models and services through a provider abstraction layer, and pitched itself as "the leading open-source AI code assistant" able to connect with any model and let teams add their own context ^[3][5].

Cloud providers

Scroll sideways for more →

Local and self-hosted options

Scroll sideways for more →

Local model support is a defining characteristic of Continue. Organizations with strict data governance requirements can run the entire system air-gapped, ensuring that source code never leaves their infrastructure ^[13].

Model roles

Continue assigns models to specific roles, and users can configure different models for each role ^[3]:

Scroll sideways for more →

How is Continue configured?

Continue is configured through a config.yaml file stored in the user's ~/.continue/ directory. The configuration uses a declarative YAML format with three required top-level properties (name, version, schema) and several optional sections ^[14].

Key configuration sections

Models: Defines which LLMs to use for each role, including provider, model name, API keys, and inference parameters such as temperature, max tokens, and stop sequences ^[14].

Rules: Provides system-level instructions that guide the AI's behavior during chat, agent, and edit interactions. Rules can be defined as inline strings in the YAML file or as separate Markdown files in a .continue/rules/ directory. Team-wide rules can be shared through the Continue Hub ^[14][15].

Context: Configures context providers that supply extra information to the AI. Built-in providers include @codebase (semantic search over the repository), @file (specific files), @docs (indexed documentation sites), @url (web page content), @terminal (terminal output), @git diff (uncommitted changes), @open (all open editor tabs), and @problems (current diagnostics) ^[10].

MCP Servers: Configures Model Context Protocol servers that give the AI access to external tools, databases, and services. MCP servers are defined with a name, command, and optional arguments. Continue supports stdio, SSE, and streamable-http transport methods ^[16].

Prompts: Custom prompt templates that can be invoked by name, replacing the older slash command system ^[14].

Docs: Documentation sites to index for the @docs context provider, allowing the AI to reference official documentation for frameworks and libraries ^[14].

Continue previously used a config.json format, but migrated to YAML starting with v1.0 to improve readability and better support multi-line content like rules ^[14].

Continue Hub and Mission Control

The Continue Hub (rebranded as Mission Control in late 2025) serves as the central platform for managing and distributing Continue configurations ^[7][15].

Blocks

The Hub organizes configurations into reusable units called "blocks." A block can be a model configuration, a set of rules, an MCP server definition, or a complete assistant profile. Blocks can be published publicly or kept private within an organization. Users reference hub blocks in their local config.yaml using a namespace format like anthropic/claude-3.5-sonnet or ollama/llama3.1-8b ^[7].

Verified partner blocks are available from companies including Anthropic, Mistral, Ollama, Voyage AI, and Docker ^[7].

Assistants

An assistant in Continue is a complete configuration that combines models, rules, MCP servers, and context providers into a ready-to-use AI coding experience. Developers can create assistants tailored to specific tech stacks, coding standards, or organizational requirements and share them through the Hub ^[7].

Pricing tiers

Mission Control offers three tiers ^[7]:

Scroll sideways for more →

Continue CLI

In 2025, Continue expanded beyond IDE extensions with the release of the Continue CLI, a command-line tool identified by the command cn. The CLI enables AI-powered code review and quality checks that can run in CI/CD environments such as GitHub Actions, Jenkins, and GitLab CI ^[8].

Installation

The CLI can be installed via npm:

npm i -g @continuedev/cli

It requires Node.js 20 or later ^[2].

Code checks

Each AI check is defined as a Markdown file stored in .continue/checks/ within a repository. These checks run as agents on every pull request and report results as GitHub status checks. Teams use them to enforce coding conventions, security patterns, architecture boundaries, and documentation standards ^[8].

Example CLI usage:

cn --config continuedev/review-bot
cn -p "Review this code for security issues" < changes.diff
cn --rule nate/spanish

The CLI can also be used interactively from the terminal for ad-hoc code analysis and generation tasks ^[8].

Which IDEs does Continue support?

Visual Studio Code

The VS Code extension was Continue's primary distribution channel, with over 2.4 million installs on the Visual Studio Marketplace. It supports Windows (x64 and ARM), macOS (Intel and Apple Silicon), Linux (x64 and ARM variants), and Alpine Linux. The extension requires VS Code version 1.70.0 or later ^[1].

The extension adds a sidebar panel for Chat and Agent modes, provides inline autocomplete suggestions, supports the Edit workflow through a keyboard shortcut overlay, and displays context providers through the @ mention interface ^[1].

JetBrains

Continue is available as a plugin for JetBrains IDEs (IntelliJ IDEA, PyCharm, WebStorm, and others) through the JetBrains Marketplace. The JetBrains plugin was community-maintained as of 2025, meaning it could lag behind the VS Code extension in feature parity. The Edit feature in JetBrains is implemented as an inline popup rather than the sidebar approach used in VS Code ^[9][11].

Privacy and data handling

Continue stores development data locally in the .continue/dev_data/ directory on the user's machine by default. No telemetry or code is sent to Continue's servers unless the user explicitly configures a cloud model provider ^[13].

When paired with local models through Ollama or llama.cpp, Continue operates entirely offline. This makes it suitable for organizations with strict compliance requirements, air-gapped environments, or developers working on proprietary codebases who cannot send code to third-party APIs ^[13].

For teams using Mission Control, Continue offers a private data plane option in the Enterprise tier, where the infrastructure runs within the customer's own cloud environment ^[7].

Model Context Protocol (MCP) integration

Continue supports the Model Context Protocol (MCP), an open standard for connecting AI models to external tools and data sources. MCP servers can be configured in config.yaml or placed as YAML files in a .continue/mcpServers/ directory at the workspace root ^[16].

MCP tools are available exclusively in Agent mode. They allow the AI to interact with external systems such as databases, issue trackers (Jira, Linear), code hosting platforms (GitHub, GitLab), error monitoring services (Sentry), security scanners (Snyk), and browser automation tools (Playwright) ^[16].

Supported transport methods include stdio (for local processes), SSE (Server-Sent Events), and streamable-http (for remote servers). Recent protocol updates have added support for parallel tool calls and explicit capability declarations ^[16].

How is Continue different from GitHub Copilot and Cursor?

Continue occupied a distinct position in the AI coding assistant market by combining open-source licensing with model flexibility.

Scroll sideways for more →

Continue's main advantage was its flexibility and transparency. Because it is fully open source, developers can inspect, modify, and self-host the entire system. Its model-agnostic design means teams are never locked into a single AI provider and can switch models as better options become available ^[3][7]. Notably, the relationship with Cursor shifted from competitor to owner when Anysphere acquired Continue in June 2026 ^[18][19].

Its main disadvantage relative to Cursor was the lack of deep codebase indexing that Cursor provides through its custom-built editor. Compared to GitHub Copilot, Continue lacked the seamless integration with the broader GitHub ecosystem (pull request reviews, issue tracking, and repository-level context) that Copilot offers natively ^[17].

Funding and business model

Continue raised a total of approximately $5.1 million across multiple rounds before its acquisition ^[4][6]:

Scroll sideways for more →

Notable angel investors include Julien Chaumond (co-founder of Hugging Face), Lisha Li (founder of Rosebud AI), and Florian Leibert (co-founder of Mesosphere). Y Combinator also participated in the funding ^[6].

The company monetized through its Mission Control platform, offering paid tiers for teams and enterprises that need governance, security, and administration features. The core IDE extensions and CLI remained free and open source under the Apache 2.0 license ^[7]. Following the June 2026 acquisition by Anysphere, Continue's standalone commercial path ended and its team and ideas moved into Cursor's stack ^[18][19].

Community

Continue maintained an active open-source community. By 2026, the project had over 34,000 GitHub stars, more than 4,900 forks, and hundreds of contributors ^[2]. The community communicated through a Discord server with over 11,000 members, a GitHub Discussions forum, and the Continue blog ^[4].

The project accepted external contributions and maintained a Code of Conduct, contributing guidelines, and a security policy. The rapid release cadence (over 800 releases) reflected the active development pace of the project before the repository was set to read-only in June 2026 following the final 2.0.0 release ^[2][18].

ELI5 (Explain Like I'm 5)

Imagine a really smart helper that lives inside the program you use to write computer code. You can chat with it, ask it to finish your sentences (lines of code), tell it to fix or change something, or even ask it to do a whole job by itself while you watch. The special thing about Continue is that you get to pick which AI brain it uses, and you can even keep that brain on your own computer so your work stays private. Continue is free and anyone can look at how it is built. In 2026, the company that makes the popular Cursor editor bought Continue, and the free version stopped getting new updates but you can still use and copy it.

See also

• GitHub Copilot
• Cursor (code editor)
• Ollama
• AI Code Generation
• Model Context Protocol
• Visual Studio Code

References

1. "Continue - open-source AI code agent." Visual Studio Marketplace. https://marketplace.visualstudio.com/items?itemName=Continue.continue ↩
2. "continuedev/continue." GitHub. https://github.com/continuedev/continue ↩
3. "Models." Continue Documentation. https://docs.continue.dev/customize/models ↩
4. "Continue: Quality control for your software factory." Y Combinator. https://www.ycombinator.com/companies/continue ↩
5. "Continue wants to help developers create and share custom AI coding assistants." TechCrunch, February 26, 2025. https://techcrunch.com/2025/02/26/continue-wants-to-help-developers-create-and-share-custom-ai-coding-assistants/ ↩
6. "Continue Launches 1.0 with Open-Source IDE Extensions and a Hub." EZ Newswire. https://www.eznewswire.com/newsroom/continue-launches-1-0-with-open-source-ide-extensions-and-a-hub-that-empowers-developers-to-build-and-share-custom-ai-code-assistants ↩
7. "Continue Launches 1.0 with Open-Source IDE Extensions and a Hub." Big Technology. https://www.bigtechnology.com/p/continue-launches-10-with-open-source ↩
8. "Beyond Code Generation: How Continue Enables AI Code Review at Scale." Continue Blog. https://blog.continue.dev/beyond-code-generation-how-continue-enables-ai-code-review-at-scale ↩
9. "Agent Quick Start." Continue Documentation. https://docs.continue.dev/ide-extensions/agent/quick-start ↩
10. "Context Providers." Continue Documentation. https://docs.continue.dev/customize/deep-dives/custom-providers ↩
11. "Edit Quick Start." Continue Documentation. https://docs.continue.dev/ide-extensions/edit/quick-start ↩
12. "Autocomplete Setup and Configuration Guide." Continue Documentation. https://docs.continue.dev/customize/deep-dives/autocomplete ↩
13. "Development data." Continue Documentation. https://docs.continue.dev/development-data ↩
14. "config.yaml Reference." Continue Documentation. https://docs.continue.dev/reference ↩
15. "Configuring Models, Rules, and Tools." Continue Documentation. https://docs.continue.dev/guides/configuring-models-rules-tools ↩
16. "How to Set Up Model Context Protocol (MCP) in Continue." Continue Documentation. https://docs.continue.dev/customize/deep-dives/mcp ↩
17. "Cursor vs GitHub Copilot vs Continue: AI Code Editor Showdown 2026." DEV Community. https://dev.to/synsun/cursor-vs-github-copilot-vs-continue-ai-code-editor-showdown-2026-2h89 ↩
18. "Cursor quietly acquires Continue, an open-source alternative to GitHub Copilot." The New Stack, June 22, 2026. https://thenewstack.io/cursor-acquires-continue-coding/ ↩
19. "Cursor Acquires Continue, Putting a Pioneering Open-Source Coding Agent Under Commercial Control." Web Developer, June 18, 2026. https://webdeveloper.com/news/cursor-acquires-continue-open-source-agent/ ↩
20. "SpaceX to acquire Cursor for $60B in stock, days after blockbuster IPO." TechCrunch, June 16, 2026. https://techcrunch.com/2026/06/16/spacex-to-acquire-cursor-for-60b-in-stock-days-after-blockbuster-ipo/ ↩