Continue website screenshot

Continue

Continue is the open-source AI code assistant for VS Code and JetBrains, distributed under Apache 2.0. The Continue IDE extensions and the Continue CLI federate to any LLM provider — Anthropic, OpenAI, Mistral, OpenRouter, Ollama, and a Continue-managed proxy — and load their configuration from Continue Hub. Continue Hub (api.continue.dev) is the registry and IDE API that serves assistants, blocks, models, rules, prompts, docs, and MCP servers to the extensions, along with free-trial status, organization policy, secrets sync, and the Stripe checkout URL for the Models Add-On. Continue has also pivoted into "continuous AI" — source- controlled checks that live as markdown files under .continue/checks/ and run in CI as GitHub status checks.

5 APIs 21 Features
AIArtificial IntelligenceDeveloper ToolsCode AssistantOpen SourceVS CodeJetBrainsCLIMCPApache 2.0

APIs

Continue Hub IDE API

REST API exposed by api.continue.dev that the Continue VS Code and JetBrains extensions and the Continue CLI use to list and refresh assistants, list organizations, fetch organi...

Continue IDE Extensions

Open-source IDE plugins shipping for VS Code and JetBrains. Provide chat, edit, apply, autocomplete, and agent modes. Bring your own LLM (Anthropic, OpenAI, Mistral, OpenRouter,...

Continue CLI

Open-source command-line interface powering Continue's source-controlled AI checks. Checks are markdown files in .continue/checks/ that run as full AI agents against pull reques...

Continue Hub

Hosted registry where teams publish and share assistants, blocks (models, rules, prompts, docs, MCP servers, context providers), and policy. Powers the Continue Hub IDE API and ...

Continue Mission Control

Observability surface for tracking check outcomes, agent runs, and adoption metrics across an organization's repositories. Part of the Team and Company tiers.

Collections

Pricing Plans

Rate Limits

Continue Dev Rate Limits

4 limits

RATE LIMITS

FinOps

Features

Open-source VS Code extension with 33k+ GitHub stars on continuedev/continue
Open-source JetBrains plugin (IntelliJ, PyCharm, GoLand, WebStorm, etc.)
Open-source Continue CLI for local and CI execution
Source-controlled AI checks (.continue/checks/*.md) that run as GitHub status checks on every PR
Source-controlled assistants (.continue/agents/*.yaml) versioned alongside code
Continue Hub registry for sharing assistants, blocks, models, rules, prompts, docs, and MCP servers
Continue Hub IDE API (api.continue.dev) with 8 REST endpoints under /ide for assistants, organizations, policy, free-trial, secrets, and checkout
BYO LLM provider — Anthropic, OpenAI, Mistral, OpenRouter, Ollama, AWS Bedrock, Google, xAI, Together AI, Cerebras, SambaNova, and more via Hub blocks
Continue-managed proxy (alwaysUseProxy=true) routes model traffic through Continue with pass-through billing
On-prem proxy option for organizations that need to keep prompt traffic inside their network
Free trial with per-user chat and autocomplete quota tracked via /ide/free-trial-status
Models Add-On purchasable via /ide/get-models-add-on-checkout-url (Stripe)
Organization policy (allowed models, secret handling, telemetry) returned by /ide/policy
Secrets sync from Hub to IDE via /ide/sync-secrets
Mission Control metrics for tracking check outcomes and agent runs across repos
Apache 2.0 license on extensions and CLI
Auto-generated TypeScript and Python SDKs from the OpenAPI spec at packages/continue-sdk
Swagger UI for local API exploration via npm run swagger-ui in packages/continue-sdk
70+ official Continue Hub blocks (per-provider repos under github.com/continuedev)
Instinct — Continue's open Next Edit model
Bearer auth with API keys prefixed con_

Use Cases

In-editor AI chat, edit, and apply

Use any frontier or local model directly inside VS Code and JetBrains without lock-in to one vendor.

Source-controlled coding standards enforced in CI

Define checks as markdown in .continue/checks/, have AI enforce them on every PR, see results as GitHub status checks.

Team-shared assistants

Publish assistants on Continue Hub so every engineer pulls the same models, rules, prompts, docs, and MCP servers.

BYO LLM cost control

Federate to a self-hosted Ollama, an OpenRouter account, or your own Anthropic/OpenAI key to keep AI spend on your existing provider.

On-prem prompt isolation

Route model traffic through an on-prem Continue proxy so prompts and secrets never leave the corporate network.

Local autocomplete with Ollama

Run code completion against a local model for zero-egress, zero-cost inference.

MCP tool integration

Compose MCP servers into a Continue assistant to give the agent access to internal tools without writing extension code.

Continuous AI

Apply Continue's "standards as checks" model to legacy codebases — codify standards in markdown, then have AI agents drag the codebase toward them.

Integrations

Anthropic

Use Claude Opus, Sonnet, and Haiku as the chat/edit/apply/autocomplete model inside Continue. Anthropic-continue-hub publishes ready-to-use blocks.

OpenAI

Use GPT-class models as Continue model providers via openai-continue-hub.

Mistral

mistral-continue-hub publishes Mistral models as Continue blocks.

OpenRouter

openrouter-continue-hub federates to any OpenRouter-hosted model.

Ollama

ollama-continue-hub points Continue at a local Ollama server for zero-egress inference.

AWS Bedrock

bedrock-continue-hub uses Bedrock-hosted models, including Claude on Bedrock.

Google

google-continue-hub federates to Gemini and Vertex AI models.

Together AI, xAI, Cerebras, SambaNova, Cohere, IBM watsonx, Novita, NCompass, Inception Labs, Relace, IONOS

Per-provider Continue Hub repositories ship blocks for each.

GitHub

Continue checks run in CI and report status checks back to the GitHub PR. The check-cli, checks-cli, and suggestions-cli automate these flows.

Slack, Sentry, Snyk

Starter tier and above can connect Continue agents to Slack, Sentry, and Snyk.

Docker

docker-continue-hub publishes Docker-authored blocks for Continue.

Model Context Protocol

Continue assistants compose MCP servers as tool sources; Continue maintains a fork of the official MCP TypeScript SDK.

Solutions

Continuous AI for engineering teams

Codify coding standards as markdown checks; AI agents enforce them in CI on every pull request.

Open-source AI IDE for any LLM

Drop-in replacement for proprietary AI coding assistants without surrendering model choice or telemetry control.

Hub-managed assistant distribution

Centralize team assistants on Continue Hub instead of per-engineer config sprawl.

Semantic Vocabularies

Continue Dev Context

0 classes · 5 properties

JSON-LD

API Governance Rules

Continue API Rules

5 rules · 2 errors 3 warnings

SPECTRAL

JSON Structure

Continue Dev Assistant Structure

7 properties

JSON STRUCTURE

Example Payloads

Resources

🔗
Website
Website
🌐
Portal
Portal
🔗
Documentation
Documentation
👥
GitHubOrganization
GitHubOrganization
👥
GitHubRepository
GitHubRepository
🔗
LinkedIn
LinkedIn
📰
Blog
Blog
📝
Signup
Signup
💰
Pricing
Pricing
🚀
GettingStarted
GettingStarted
🔗
Documentation
Documentation
🔗
Documentation
Documentation
🔗
ChecksDocs
ChecksDocs
🔗
Hub
Hub
🔗
License
License
📦
SDKs
SDKs
📦
SDKs
SDKs
🔧
Tools
Tools
🔧
Tools
Tools
🔧
Tools
Tools
🔧
Tools
Tools
💻
CodeExamples
CodeExamples
💻
CodeExamples
CodeExamples
🔗
Plugins
Plugins
🔗
Plugins
Plugins
🔗
Plugins
Plugins
🔗
Plugins
Plugins
🔗
Plugins
Plugins
🔗
Plugins
Plugins
🔗
SpectralRules
SpectralRules
🔗
Vocabulary
Vocabulary
🔗
Plans
Plans
🔗
RateLimits
RateLimits
🔗
FinOps
FinOps
🔗
LlmsText
LlmsText

Sources

Raw ↑
opencollection: 1.0.0
info:
  name: Continue Hub IDE API
  version: 1.0.0
items:
- info:
    name: List Assistants for IDE
    type: http
  http:
    method: GET
    url: https://api.continue.dev/ide/list-assistants
    params:
    - name: alwaysUseProxy
      value: ''
      type: query
      description: Whether to always use the Continue-managed proxy for model requests
    - name: organizationId
      value: ''
      type: query
      description: ID of the organization to scope assistants to. If not provided, personal assistants are returned.
    auth:
      type: bearer
      token: '{{bearerToken}}'
  docs: 'Returns a complete list of assistants available to the user, with their full configurations,

    icons, and other metadata needed by the IDE to display and use them.


    This endpoint performs a full refresh of the list of assistants, including unrolling

    configurations and resolving secrets.

    '
- info:
    name: Get a Specific Assistant by Slug
    type: http
  http:
    method: GET
    url: https://api.continue.dev/ide/get-assistant/:ownerSlug/:packageSlug
    params:
    - name: ownerSlug
      value: ''
      type: path
      description: Slug of the user or organization that owns the assistant
    - name: packageSlug
      value: ''
      type: path
      description: Slug of the assistant package
    - name: alwaysUseProxy
      value: ''
      type: query
      description: Whether to always use the Continue-managed proxy for model requests
    - name: organizationId
      value: ''
      type: query
      description: ID of the organization to scope assistants to. If not provided, personal assistants are returned.
    auth:
      type: bearer
      token: '{{bearerToken}}'
  docs: 'Returns a single assistant configuration by its owner and package slug.

    This endpoint is useful when you need to retrieve or refresh a specific assistant

    without fetching the entire list.

    '
- info:
    name: Get Free Trial Status for User
    type: http
  http:
    method: GET
    url: https://api.continue.dev/ide/free-trial-status
    auth:
      type: bearer
      token: '{{bearerToken}}'
  docs: 'Returns the current free trial status for the authenticated user, including

    usage counts and limits for chat and autocomplete features.

    '
- info:
    name: Get Stripe Checkout URL for Models Add-On
    type: http
  http:
    method: GET
    url: https://api.continue.dev/ide/get-models-add-on-checkout-url
    params:
    - name: profile_id
      value: ''
      type: query
      description: Profile ID to include in the callback URL
    - name: vscode_uri_scheme
      value: ''
      type: query
      description: VS Code URI scheme to include in the callback URL
    auth:
      type: bearer
      token: '{{bearerToken}}'
  docs: 'Creates a Stripe checkout session for the models add-on subscription

    and returns the checkout URL.

    '
- info:
    name: Get Organization Policy
    type: http
  http:
    method: GET
    url: https://api.continue.dev/ide/policy
    auth:
      type: bearer
      token: '{{bearerToken}}'
  docs: 'Returns the policy configuration for the first organization

    that the user belongs to which has a policy configured.

    '
- info:
    name: Synchronize Secrets for User
    type: http
  http:
    method: POST
    url: https://api.continue.dev/ide/sync-secrets
    body:
      type: json
      data: '{}'
    auth:
      type: bearer
      token: '{{bearerToken}}'
  docs: 'Resolves and synchronizes secrets for the authenticated user based on

    the provided Fully Qualified Secret Names (FQSNs).

    '
- info:
    name: List Assistant Full Slugs
    type: http
  http:
    method: GET
    url: https://api.continue.dev/ide/list-assistant-full-slugs
    auth:
      type: bearer
      token: '{{bearerToken}}'
  docs: 'This endpoint is temporarily disabled and returns a 429 status code

    to prevent constant refreshes of the full assistant list until a

    fixed client version can be deployed.

    '
- info:
    name: List Organizations for User
    type: http
  http:
    method: GET
    url: https://api.continue.dev/ide/list-organizations
    auth:
      type: bearer
      token: '{{bearerToken}}'
  docs: 'Returns a list of organizations that the authenticated user belongs to,

    including organization metadata and pre-signed icon URLs.

    '
bundled: true