Continue
Continue is an open-source AI programming assistant plugin for mainstream code editors including VS Code and JetBrains IDEs, designed to integrate large language model capabilities into development workflows. It supports code auto-completion, conversational code generation and editing, and codebase question answering. Users can configure connections to multiple AI models and external tool services, enabling developers to leverage AI capabilities directly within their editor to improve programming efficiency.
Core Facts
For applications with high call volumes, the total cost of self-hosted open-source model deployment is often significantly lower than using commercial APIs.
Mainstream development tools such as Cursor, Windsurf, and VS Code already support the MCP protocol.
Continue is an open-source VS Code/JetBrains plugin that supports connecting to multiple model backends including OpenAI, Anthropic, and local Ollama.
Timeline (last 90 days)
Connecting local models to VS Code can be done through third-party extensions (such as Continue or LM Studio's Copilot extension) or VS Code's native "Manage Language Models" feature (with a custom endpoint pointing to LM Studio), and the latter requires no cloud account login.
Continue leans toward inline completion and chat, while Cline leans toward Agent-style operations with file read/write and command execution capabilities.
Using VS Code open-source extensions (such as Continue and Cline) together with code models running locally via Ollama can achieve fully offline, zero-cost, zero-network AI programming assistance, but the hardware requires at least 16GB of memory.
T3-tier (general) tools have a composite score of about 6, including Continue, Zed, Baidu Comet, WorkBody, GLM Tongyi Lingma and others.
The T3 tier includes Continue, Zed, Baidu Comet, WorkBody, and GLM, defined as always having some problems in use.
Installing the Continue plugin in VS Code and pointing the API address to local Strata allows you to use an AI coding assistant in an offline environment.
Using Strata's local interface together with VS Code and the Continue plugin enables a code assistant usable offline, with code never leaving the local computer.
Competition in the AI coding assistant track is increasingly fierce, with major players including tools such as Cline, Cursor, and Continue.
A tool that conforms to the MCP protocol only needs to be implemented once to be callable by ChatGPT, Claude Desktop, Cursor, Continue and any other client that supports the protocol.
MCP allows projects like REA, as an npm package, to be plug-and-play for MCP-supporting clients such as Claude Desktop, Cursor and Continue.
27 more timeline events
All Facts (20)
For applications with high call volumes, the total cost of self-hosted open-source model deployment is often significantly lower than using commercial APIs.
80%VerifiedMainstream development tools such as Cursor, Windsurf, and VS Code already support the MCP protocol.
80%VerifiedContinue is an open-source VS Code/JetBrains plugin that supports connecting to multiple model backends including OpenAI, Anthropic, and local Ollama.
80%VerifiedUsing a routing mechanism to distribute requests to models of different scales based on task complexity can reduce the average call cost at the overall level.
75%VerifiedThe API aggregation layer is typically built on the OpenAI-compatible interface specification, allowing existing tools to connect simply by modifying the endpoint address.
65%VerifiedIDE plugins such as Cursor, Continue, and Cline natively support the OpenAI-compatible interface format.
65%UnverifiedDeepSeek可以集成到VS Code、JetBrains系列IDE中，通过Continue、Codeium等插件实现智能代码补全、代码审查、文档自动生成等功能
85%UnverifiedContinue是一个开源AI编程助手框架，允许开发者自由选择后端模型，包括本地部署的Code Llama、DeepSeek Coder等开源模型
85%Unverified终端AI工具赛道在2024-2025年间经历了爆发式增长，参与者包括GitHub Copilot CLI、Gemini CLI、Anthropic的Claude Code、Cursor的终端集成以及Aider、Continue等开源项目
75%UnverifiedConnecting local models to VS Code can be done through third-party extensions (such as Continue or LM Studio's Copilot extension) or VS Code's native "Manage Language Models" feature (with a custom endpoint pointing to LM Studio), and the latter requires no cloud account login.
50%UnverifiedContinue leans toward inline completion and chat, while Cline leans toward Agent-style operations with file read/write and command execution capabilities.
50%UnverifiedUsing VS Code open-source extensions (such as Continue and Cline) together with code models running locally via Ollama can achieve fully offline, zero-cost, zero-network AI programming assistance, but the hardware requires at least 16GB of memory.
50%UnverifiedT3-tier (general) tools have a composite score of about 6, including Continue, Zed, Baidu Comet, WorkBody, GLM Tongyi Lingma and others.
50%UnverifiedThe T3 tier includes Continue, Zed, Baidu Comet, WorkBody, and GLM, defined as always having some problems in use.
50%UnverifiedInstalling the Continue plugin in VS Code and pointing the API address to local Strata allows you to use an AI coding assistant in an offline environment.
50%UnverifiedUsing Strata's local interface together with VS Code and the Continue plugin enables a code assistant usable offline, with code never leaving the local computer.
50%UnverifiedCompetition in the AI coding assistant track is increasingly fierce, with major players including tools such as Cline, Cursor, and Continue.
50%UnverifiedA tool that conforms to the MCP protocol only needs to be implemented once to be callable by ChatGPT, Claude Desktop, Cursor, Continue and any other client that supports the protocol.
50%UnverifiedMCP allows projects like REA, as an npm package, to be plug-and-play for MCP-supporting clients such as Claude Desktop, Cursor and Continue.
50%UnverifiedContinue, Cline and Aider are plugins that support multiple backends and can switch models by task type within the same editor.
50%