mistralai-workflows
Mistral Workflows - Build reliable AI workflows with Python
Decision gist · record as of 2026-08-14
Yes, if you are building production AI workflows with Mistral AI and need built-in reliability, distributed execution, and observability. The low install friction and active maintenance are strong signals. However, the Beta status, Python 3.12+ requirement, and temporalio dependency complexity mean you should verify that the maturity level and backend setup align with your deployment model before committing to a large workflow system.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.12 or later; temporalio dependency may require additional system setup for workflow persistence and distributed coordination.
- Low install friction with a pure-wheel distribution.
- Active maintenance (released 3 days ago).
License · maintenance · safety
Apache-2.0 (permissive) — Apache-2.0 permissive license allows commercial use, modification, and distribution with minimal restrictions—standard for open-source infrastructure.
last release 2026-08-11 (3 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 196,477 downloads/mo, #9,785 on PyPI
Alternatives
Verify before relying
pip install mistralai-workflows
from mistralai.workflows import workflow, activity
from datetime import timedelta
@activity
async def get_weather(city: str) -> str:
return f"Weather in {city}: Sunny"
@workflow.define
class WeatherWorkflow:
@workflow.run
async def run(self, city: str) -> str:
weather = await workflow.execute_activity(
get_weather, city, start_to_close_timeout=timedelta(seconds=10)
)
return weather- Whether temporalio backend requires external service deployment or can run in-process for development.
- Performance characteristics and scalability limits for concurrent workflows.
- Maturity and stability guarantees given Beta development status.
What it is and what it does
Mistral Workflows is a Python framework for defining and executing reliable, distributed AI workflows using decorators and async/await syntax. It wraps Mistral AI LLM calls and custom activities (tasks) into workflows with automatic retry logic, timeouts, and exactly-once execution semantics. The SDK is built on temporalio for durability and state management, integrates the opentelemetry stack for observability, and uses Pydantic for type validation.
You define activities (individual tasks) and workflows (orchestrations of activities) using Python decorators, then execute them with built-in fault tolerance and distributed scaling. It's aimed at production AI applications that need reliability guarantees—retries on failure, timeout enforcement, and structured logging—without manually implementing those patterns.
Use it for
- Build multi-step LLM pipelines (e.g., research → analysis → report generation) with automatic retries and timeout protection.
- Orchestrate long-running AI tasks across multiple workers with exactly-once semantics and durable state.
- Integrate Mistral AI calls with external APIs and custom Python logic in a single declarative workflow.
- Monitor and trace distributed AI workflows using built-in OpenTelemetry instrumentation.
- Deploy fault-tolerant AI agents that survive worker failures and resume from checkpoints.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are building production AI workflows with Mistral AI and need built-in reliability, distributed execution, and observability.
The low install friction and active maintenance are strong signals. However, the Beta status, Python 3.12+ requirement, and temporalio dependency complexity mean you should verify that the maturity level and backend setup align with your deployment model before committing to a large workflow system.
Install
mistralai-workflows on PyPI
Before you install
Low install friction with a pure-wheel distribution. Active maintenance (released 3 days ago). Requires Python 3.12–3.14 and pulls in 17 runtime dependencies including temporalio, httpx, and observability libraries (opentelemetry stack), which adds moderate complexity to your environment.
Requires Python 3.12 or later; temporalio dependency may require additional system setup for workflow persistence and distributed coordination.
License in practice
Apache-2.0 permissive license allows commercial use, modification, and distribution with minimal restrictions—standard for open-source infrastructure.
Quickstart
pip install mistralai-workflows
from mistralai.workflows import workflow, activity
from datetime import timedelta
@activity
async def get_weather(city: str) -> str:
return f"Weather in {city}: Sunny"
@workflow.define
class WeatherWorkflow:
@workflow.run
async def run(self, city: str) -> str:
weather = await workflow.execute_activity(
get_weather, city, start_to_close_timeout=timedelta(seconds=10)
)
return weatherVerify before relying
- Whether temporalio backend requires external service deployment or can run in-process for development.
- Performance characteristics and scalability limits for concurrent workflows.
- Maturity and stability guarantees given Beta development status.
Package facts
| License | Apache-2.0 permissive |
| Python support | Supports the current Python release <3.15,>=3.12 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 17 packagesasynciolimiterhttpxjsonpatchmistralaiopentelemetry-apiopentelemetry-exporter-otlp-proto-httpopentelemetry-instrumentation-httpxopentelemetry-sdkorjsonpydantic-settingspydanticpyjwtstarlettestructlogtemporaliotenacityurllib3 |
| Maintenance | Actively maintained 3 days since the last release |
| First released | |
| Downloads | 196,477 / month, #9,785 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaIntended Audience :: DevelopersLicense :: OSI Approved :: Apache Software LicenseProgramming Language :: Python :: 3Programming Language :: Python :: 3.12Topic :: Scientific/Engineering :: Artificial IntelligenceTopic :: Software Development :: Libraries :: Python Modules |
Evidence: mistralai_workflows-3.11.0-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 › “ai workflow orchestration python”
- mistralai-workflowsMistral Workflows is a Python SDK for building AI-powered workflows…
- kailash-enterpriseA Rust-compiled workflow orchestration engine that executes the same…
- langflowLangflow is a visual platform for building, testing, and deploying AI…
Give your agent the search over MCP, or paste the wish link into any chat.
More Python Modules packages
Converts domain names between Unicode and ASCII-compatible encoding (Punycode) according to IDNA 2008 and Unicode Technical Standard 46, with security validation and broader script coverage than the standard library.
Install it if you work with internationalized domain names, need to validate domains, or use HTTP clients that depend on it transitively.
Setuptools is a Python build backend and package management tool that handles building, distributing, and installing Python packages, including support for C/C++ extension modules.
PyYAML parses and emits YAML 1.1 data format, enabling serialization and deserialization of configuration files and Python objects to and from human-readable YAML text.
Pydantic validates Python data structures against type hints, coercing and checking input at runtime to ensure it matches a declared schema.
Provides reusable metadata objects for use with PEP-593 `typing.Annotated` to express common constraints like bounds, collection sizes, and predicates on types.
Install it if you use or build libraries that need to express type constraints in a standardized, inspectable way—or if you want to annotate your own types with…
Provides runtime tools to inspect and introspect Python type annotations, enabling programmatic examination of type hints at execution time.
See also mistralai · temporalio · opentelemetry-instrumentation-mistralai · vellum-ai · mistral_common · simpleflow · langchain-mistralai · langflow-base · hatchet-sdk · mistral-vibe