ASSISTANTS

BLOCKS

BUNDLES

Trending blocks

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

Learn more

Explore custom AI blocks

The following blocks are popular in the Continue community

GPT OSS 120B

gpt-oss-120b-GGUF

Semgrep MCP

A Model Context Protocol (MCP) server for using Semgrep to scan code for security vulnerabilities. Secure your vibe coding! This is actively supported but should be considered beta software. It's still experimental and may break at any time. Performance improvements, and OAuth are being worked on

drewsepeczi/airbnb

Airbnb coding styles for React/JSX

qwen2.5-coder 14b

Qwen2.5 Coder 32B Instruct (free)

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

Linear MCP

The Linear MCP server has tools available for finding, creating, and updating objects in Linear like issues, projects, and comments — with more functionality on the way. Linear's MCP server follows the authenticated remote MCP spec, so the server is centrally hosted and managed. Learn more: https://linear.app/docs/mcp

GLM-4.5

Sentry MCP

Provides a secure way of bringing Sentry's full issue context into systems that are able to leverage MCP. Sentry hosts and manages a remote MCP server, which you can connect to and leverage centrally. Read more: https://docs.sentry.io/product/sentry-mcp/

PHP Docs

Qwen3 30B A3B GGUF

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support.

starter/vue-rules

deepseek-r1 14b

Gemini 1.5 Pro

MCP Python SDK

qwen2.5-coder 7b

Check SOLID

Check how well a piece of code follows SOLID principles.

GitHub PR / Commit Workflow

gpt-oss 120b

o3-pro

Pull Request Description Rules

Generate comprehensive pull request descriptions from commit history and changes Use when: Creating PR/MR descriptions, analyzing commit ranges between branches, or documenting feature implementations Input: Git commit history, commit ranges (e.g., main..feature-branch), branch comparisons Output: Structured markdown with summary, changes, breaking changes, and testing notes

starter/rust-rules

starter/java-rules

DeepSeek Coder 6.7B

deepseek-coder:6.7b

Playwright e2e test

Qwen2.5 Coder 32B Instruct GGUF

State-of-the-art code LLM with 32B parameters, matching GPT-4o coding abilities. Enhanced code generation, reasoning and fixing capabilities. https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct-GGUF

OpenRouter moonshotai/kimi-k2:free

https://openrouter.ai/moonshotai/kimi-k2:free

OpenRouter_model

Openrouter - deepseek - free model.

Gemini 2.5 Flash 05-20

Filesystem MCP

Local filesystem access with configurable allowed paths

Qwen 1.5 7B Chat Hybrid

The AMD Qwen-1.5-7B-Chat-Hybrid model is a quantized 7B parameter chat language model designed for hybrid execution across both the NPU and integrated GPU on AMD Ryzen AI-powered PCs. It’s intended for efficient, high-performance local inference using AMD’s OnnxRuntime GenAI framework, maximizing the capabilities of consumer AMD hardware. https://huggingface.co/amd/Qwen1.5-7B-Chat-awq-g128-int4-asym-fp16-onnx-hybrid

Trending blocks