Trending blocks

Gemini's newest multimodal model, with next generation features and improved capabilities

OpenAI's versatile, high-intelligence flagship model

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

Local filesystem access with configurable allowed paths

OpenAI's fast, affordable small model for focused tasks

Knowledge graph-based persistent memory system

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

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

With Browser MCP, you can use MCP to automate your browser so that AI applications can navigate the web, fill out forms, and more. https://browsermcp.io/

References the contents of all your open files, providing a quick overview of the active code across your development environment.

GitHub repository access and management

References the currently open file, providing quick access to its contents for immediate review or modification.

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

xAI's previous frontier language model with state-of-the-art reasoning capabilities

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

References any file in your current workspace, providing easy access to its contents for quick review or editing.

OpenAI's most recent small reasoning model, providing high intelligence at the same cost and latency targets of o1-mini

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

Shows the structure of your codebase, making it easier to navigate files and directories.

Cutting-edge language model for coding. With the second version released January 2025, Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.

Anthropic's previous most intelligent model

Anthropic's most intelligent model with toggleable extended thinking

Git Rules

The Exa MCP server enables AI assistants to perform web searches using Exa's powerful search API, providing structured search results including titles, URLs, and content snippets

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

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

Web and local search using Brave's Search API