# Continue Coding agent for the editor and terminal with configurable models and tools. Canonical profile: https://ki-agentenkompass.de/en/agents/continue/ Editor: [Michael Meierhoff](https://ki-agentenkompass.de/en/about/) Sources reviewed: 2026-10-26 Basis: provider documentation. Examples are editorial suggestions, not hands-on product tests. ## Overview Available offering; access methods and prerequisites are described separately in this profile. - Provider: Continue - Product family: Continue - Profile type: Coding agent - Environment: Own computer or server - Connections: Edit files, Run commands, Terminal, Automated tasks, Configuration - Setup: Install the editor extension or CLI; the CLI requires a Continue account or Anthropic API key. - Pricing model: Model costs depend on the selected access method. A current flat platform price is not confirmed by the reviewed sources. ## Key features ### Edit files Read and edit project files. Source: https://docs.continue.dev/cli/quickstart ### Run commands Run commands for multi-step development tasks. Source: https://docs.continue.dev/cli/quickstart ### Terminal Use the agent interactively in the terminal. Source: https://docs.continue.dev/cli/quickstart ### Automated tasks Start headless tasks from scripts. Source: https://docs.continue.dev/cli/quickstart ### Configuration Configure models, assistants and MCP servers. Source: https://docs.continue.dev/cli/quickstart ## Example workflows ### Edit files - Your input: Read and edit project files. - Possible result: A work product for your review. - What to check: Review results and write actions before accepting them. ### Run commands - Your input: Run commands for multi-step development tasks. - Possible result: A work product for your review. - What to check: Review results and write actions before accepting them. ## Requirements and limits ### Setup Requirement: Install the editor extension or CLI; the CLI requires a Continue account or Anthropic API key. Source: https://docs.continue.dev/cli/quickstart ### Usage costs Limitation: Model costs depend on the selected access method. A current flat platform price is not confirmed by the reviewed sources. Source: https://docs.continue.dev/ ### Output quality Not yet confirmed: Review results and write actions before accepting them. Source: https://docs.continue.dev/cli/quickstart ## A good fit if … - you want to automate coding tasks in the terminal or CI with cn -p - you want to confirm write and Bash actions yourself before they run - you want to sign in with a Continue account or your own Anthropic API key ## Less suitable if … - you need a managed solution with administrator approvals for a team; the reviewed pages describe none - you need built-in schedules and failure notifications without your own scripts; the reviewed pages describe none Editorial assessment based on provider documentation. Not a product test. ## Usable AI models Open choice You add your models to config.yaml yourself, with your own key and a provider such as OpenAI, Anthropic or Mistral. OpenRouter gives you its model catalog, Ollama gives you local models, and apiBase also lets you use your own OpenAI-compatible endpoint. Agent mode requires a model that supports tools. - Model families named: OpenAI (GPT), Anthropic (Claude), Mistral · Other models can be connected freely - Model choice: You choose - Your own API key: Yes - Router or custom endpoint: Yes - Local models: Yes Documented · Sources accessed on: 2026-11-05 - [Continue: config.yaml reference](https://docs.continue.dev/reference) - [Continue: Ollama](https://docs.continue.dev/customize/model-providers/top-level/ollama) - [Continue: OpenRouter](https://docs.continue.dev/customize/model-providers/top-level/openrouter) ## Europe & regional availability Consider installation and provider access separately. A complete regional feature matrix is not published. Reviewed scope: Product access in Germany and the EU Reviewed on: 2026-10-26 ### Access and connected services With requirements Install the editor extension or CLI; the CLI requires a Continue account or Anthropic API key. Region covered: Germany / EU Documented reason: The reviewed sources document no specific restriction caused by the AI Act, DMA or GDPR. Model and service access depend on country and contract. Official source: https://docs.continue.dev/cli/quickstart Official source: https://docs.continue.dev/ ## Accounts & permissions Based on provider documentation. Permissions depend on the account, integration and organization policies. Review the permissions actually requested before use. Configuration covered: Continue CLI (cn) on your own machine; the VS Code and JetBrains extension is only touched on Sources reviewed: 2026-11-05 ### Account used Documented: You sign in to a Continue account in the browser with cn login, or enter an Anthropic API key on first launch. For scripts and CI you set the CONTINUE_API_KEY environment variable. Evidence: https://docs.continue.dev/cli/quickstart ### Admin approval Open in reviewed sources: The reviewed pages describe no approval or restriction by organisation administrators. The tool permissions page covers local rules, flags and a permissions file. Evidence: https://docs.continue.dev/cli/tool-permissions ### Data access & team sharing Documented: Read-only tools are allowed by default; write tools and Bash ask first. With --readonly (plan mode) write tools are excluded while reads and Bash stay allowed; with --auto everything runs without prompting. Rules can be narrowed with glob patterns on arguments such as file paths. Evidence: https://docs.continue.dev/cli/tool-permissions Evidence: https://docs.continue.dev/cli/quickstart ## Prices and included usage Pricing checked: 2026-10-26 Model costs depend on the selected access method. A current flat platform price is not confirmed by the reviewed sources. Model costs depend on the selected access method. A current flat platform price is not confirmed by the reviewed sources. Pricing details: https://docs.continue.dev/ ## Operation & oversight Based on public provider documentation. Assessments are editorial inferences from the stated properties. Actual time requirements and reliability have not been measured. Deployment covered: Continue CLI in the terminal (interactive) and in headless mode for scripts Sources reviewed: 2026-11-05 ### Files and working state Open in reviewed sources: Persistent permissions are stored in ~/.continue/permissions.yaml. The headless page does not document how working state is kept between individual headless runs. Evidence: https://docs.continue.dev/cli/tool-permissions Evidence: https://docs.continue.dev/cli/headless-mode ### Sign-ins Open in reviewed sources: The reviewed pages do not say how long a cn login sign-in or an API key remains valid. Evidence: https://docs.continue.dev/cli/quickstart ### Starting further runs Documented with conditions: You start runs yourself: interactively with cn or as a single task with cn -p, for example in CI pipelines or git hooks. The headless page describes no built-in schedule. Evidence: https://docs.continue.dev/cli/headless-mode ### Human intervention Documented: Write tools and Bash ask for approval by default (TUI only). In headless mode, tools that would ask are excluded; flags such as --allow enable them, and --allow "*" allows everything. Evidence: https://docs.continue.dev/cli/tool-permissions Evidence: https://docs.continue.dev/cli/headless-mode ### Detecting errors Open in reviewed sources: There is a --verbose flag for verbose logging. The reviewed pages say nothing about log location, exit codes or failure notifications. Evidence: https://docs.continue.dev/cli/quickstart Evidence: https://docs.continue.dev/cli/headless-mode ### Resuming after failures Documented with conditions: With cn -p --resume you can resume a previous session without interaction; the earlier history is replayed. The headless page does not describe automatic retries. Evidence: https://docs.continue.dev/cli/headless-mode ### Editorial assessment Control is yours: using --auto or --allow "*" removes the prompts, and plan mode still allows Bash. For unattended runs you must plan permissions, logging and retries yourself. ## Memory and conversation continuity Scope: Continue IDE and cn CLI Sources accessed: 2026-11-04 Persistent rules and resumable chats; automatic fact memory is not established. ### Storage and scope Partly documented: Configuration files and rules provide persistent instructions; earlier chats can be resumed. A separate learned fact store and its storage location are not described. - [Continue config.yaml Reference](https://docs.continue.dev/reference) - [Continue TUI Mode](https://docs.continue.dev/cli/tui-mode) - [Continue CLI Quickstart](https://docs.continue.dev/cli/quickstart) ### Selection and timing Partly documented: Rules are added to system context; /init generates project instructions. Automatic conversation extraction into long-term memory is not documented. - [Continue config.yaml Reference](https://docs.continue.dev/reference) - [Continue TUI Mode](https://docs.continue.dev/cli/tui-mode) - [Continue CLI Quickstart](https://docs.continue.dev/cli/quickstart) ### Inspect, edit and delete Partly documented: Rules are editable configuration; /clear clears chat. A separate memory list with fact editing is not documented. - [Continue config.yaml Reference](https://docs.continue.dev/reference) - [Continue TUI Mode](https://docs.continue.dev/cli/tui-mode) - [Continue CLI Quickstart](https://docs.continue.dev/cli/quickstart) ### Agent and channel boundaries Documented: Rules and context follow the selected agent configuration and project files. Chat resumption refers to a specific earlier session. - [Continue config.yaml Reference](https://docs.continue.dev/reference) - [Continue TUI Mode](https://docs.continue.dev/cli/tui-mode) - [Continue CLI Quickstart](https://docs.continue.dev/cli/quickstart) ### Retrieval Documented: Rules are inserted into system messages; @ references load files. /resume restores conversation history; knowledge context is distinct from learned memory. - [Continue config.yaml Reference](https://docs.continue.dev/reference) - [Continue TUI Mode](https://docs.continue.dev/cli/tui-mode) - [Continue CLI Quickstart](https://docs.continue.dev/cli/quickstart) ### Session reset and compaction Documented: /compact summarizes chat, /clear clears it and /resume continues an earlier chat. /fork branches the current history. - [Continue config.yaml Reference](https://docs.continue.dev/reference) - [Continue TUI Mode](https://docs.continue.dev/cli/tui-mode) - [Continue CLI Quickstart](https://docs.continue.dev/cli/quickstart) ## Context Review results and write actions before accepting them. Official sources reviewed. Example tasks are editorial suggestions; hands-on testing is outstanding. ## Open points Requirements and limits, not yet confirmed: - Output quality ## Sources - https://docs.continue.dev/cli/quickstart - https://docs.continue.dev/ ## Provider Coding agent for the editor and terminal with configurable models and tools. - Operator: Continue - Organization: Provider - Website: https://docs.continue.dev/cli/quickstart - Reviewed: 2026-10-26 - Provider source: https://docs.continue.dev/cli/quickstart - Provider source: https://docs.continue.dev/ [Sources and method](https://ki-agentenkompass.de/en/sources/)