mistralai-vibe-sdk

What it is and what it does

Mistralai Vibe SDK is a Python framework for building and running AI agents powered by Mistral's language models. It provides stateful async and sync sessions, Pydantic-based tool authoring, built-in filesystem tools, and client-handled tools for UI-dependent actions. The SDK also supports Skills—reusable instruction sets that are advertised in the prompt and loaded on demand—and integrates with MCP (Model Context Protocol) servers to discover and expose their tools to the agent.

The package is designed for developers who want to orchestrate multi-turn agent interactions with streaming support, event-driven callbacks, and direct access to task protocol events. It handles tool result metadata separately from model-visible results, supports local stdio-based MCP servers and connector-backed servers via Mistral's infrastructure, and includes examples ranging from basic REPL interactions to advanced task-protocol workflows.

Use it for:

• Build a multi-turn conversational agent that can call custom tools and filesystem operations with streaming updates to the UI.
• Integrate external MCP servers (local or Mistral-hosted) to expose their capabilities within an agent's decision-making loop.
• Implement structured task workflows where an agent discovers and loads task-specific instruction sets (Skills) on demand.
• Create agents that handle user-dependent actions like prompting for confirmation or input, with metadata annotations for non-model consumers.
• Run end-to-end agentic pipelines locally or via HTTP with direct access to task state updates and result events.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Python SDK for building and running Vibe agents with stateful async/sync sessions, Pydantic-based tool authoring, and MCP server integration.

Yes, if you are building agents with Mistral models and need a structured, async-first framework with tool authoring and MCP integration. The low install friction, active maintenance, and recent release are positive signals. However, verify the license status before production use, and confirm Python 3.12+ is available in your environment. No known vulnerabilities as of the query date.

Install

mistralai-vibe-sdk on PyPI

pip install mistralai-vibe-sdk

uv add mistralai-vibe-sdk

poetry add mistralai-vibe-sdk

Installing mistralai-vibe-sdk

Before you install

Low install friction with a pure-Python wheel. Active maintenance with a recent release (16 days old). Requires Python 3.12 or later. Nine runtime dependencies including httpx, pydantic, and mistralai suggest a well-integrated ecosystem.

License in practice

License status is unclear—no SPDX identifier or raw license text is available in the package metadata. Verify the actual license terms before adopting in production or commercial contexts.

Quickstart

from mistralai.vibe.sdk import Agent, AgentConfig
from mistralai.vibe.sdk.providers.completion import MistralCompletionConfig

agent = Agent(
    config=AgentConfig(
        completion=MistralCompletionConfig(model="mistral-large-latest"),
        system_prompt="You are a concise assistant.",
    )
)

async with agent.session() as session:
    state = await session.run_to_completion("Hello")
    print(state.output)

Requires Python 3.12 or later. Requires MISTRAL_API_KEY environment variable or explicit API key configuration for Mistral completion models.

Verify before relying

• Whether the unclear license status reflects a missing declaration or an intentionally permissive/proprietary choice.
• Whether MCP server integration supports all MCP protocol versions or has version constraints.
• Real-world performance characteristics and latency for streaming vs. completion modes.

Package facts

Evidence: mistralai_vibe_sdk-0.12.1-py3-none-any.whl

Tags

More Artificial Intelligence packages