mistralai-vibe-sdk
Vibe SDK
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.12 or later.
- Requires MISTRAL_API_KEY environment variable or explicit API key configuration for Mistral completion models.
- Low install friction with a pure-Python wheel.
License · maintenance · safety
(unclear) — 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.
last release 2026-07-29 (16 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 151,732 downloads/mo, #10,921 on PyPI
Alternatives
Verify before relying
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)- 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.
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 on it.
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
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.
Requires Python 3.12 or later. Requires MISTRAL_API_KEY environment variable or explicit API key configuration for Mistral completion models.
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)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
| License | Not declared unclear |
| Python support | Supports the current Python release >=3.12 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 9 packagescertifipydantichttpxmarkdownifymistralaistructlogstarlettetenacitymcp |
| Maintenance | Actively maintained 16 days since the last release |
| First released | |
| Downloads | 151,732 / month, #10,921 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
Evidence: mistralai_vibe_sdk-0.12.1-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “tool authoring framework”
- mistralai-vibe-sdkPython SDK for building and running Vibe agents with stateful…
- openrewriteOpenRewrite Python provides a framework for authoring and testing…
- cloudformation-cliA command-line tool for authoring and managing AWS CloudFormation…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also mistral-vibe · mistralai · praisonaiagents · strands-agents · composio · langchain-mistralai · pydantic-deep · toolbox-adk · PraisonAI