ASSISTANTS

BLOCKS

BUNDLES

New blocks

Blocks are reusable components that define specific behaviors and capabilities for AI assistants, from custom instructions to advanced model configurations

Learn more

Explore new blocks

The following blocks were recently created by the Continue community

Gemini 2.0 Flash Thinking

Models

Playwright MCP Server

This server enables LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser environment using Playwright.

Gemini text-embedding-004

Models

OpenAI text-embedding-3-large

OpenAI's larger embedding model that creates embeddings with up to 3072 dimensions

Models

Angular Docs

Angular Rules

Rules

PyTorch Docs

Next.js Rules

Rules

Nuxt Docs

Nuxt Rules

Rules

PyTorch Rules

Rules

Next.js Docs

Svelte Docs

Svelte Rules

Rules

Azure Blob Storage Dev Data

Data

Google Cloud Storage Dev Data

Data

S3 Dev Data

Data

Claude 3.5 Sonnet

Models

CodeGate Anthropic

Models

deepseek-r1-distill-llama-70b

Models

deepseek-r1-distill-qwen-32b

Models

deepseek-r1

DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks

Models

meta-llama-3.1-70b-instruct

Models

qwen2.5-coder-32b-instruct

The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing

Models

dlt+ MCP

MCP server equipped with tools with tools to interact with your dlt+ project. The `uv` package manager is required. Don't install both the dlt and the dlt+ MCP servers to avoid redundant tools. Reach out for an early access dlt+ license: https://dlthub.com/docs/plus/intro