Build AI agents with the Mistral Agents API
Today we announce our new Agents API, a major step forward in making AI more capable, useful, and an active problem-solver.
Traditional language models excel at generating text but are limited in their ability to perform actions or maintain context. Our new Agents API addresses these limitations by combining Mistral's powerful language models with:
- Built-in connectors for code execution, web search, image generation, and MCP tools
- Persistent memory across conversations
- Agentic orchestration capabilities
The Agents API complements our Chat Completion API by offering a dedicated framework that simplifies implementing agentic use cases. It serves as the backbone of enterprise-grade agentic platforms.
By providing a reliable framework for AI agents to handle complex tasks, maintain context, and coordinate multiple actions, the Agents API enables enterprises to use AI in more practical and impactful ways.
Mistral agents in action.
Explore the diverse applications of Mistral’s Agents API across various sectors:
Coding assistant with Github.
An agentic workflow built with Mistral's agents API where an agent interacts with Github and oversees a developer agent, powered by DevStral to write code. The agent is granted full authority over Github, showcasing automated software development task management.
Linear tickets assistant.
An intelligent task coordination assistant powered by our Agents API, using multi-server MCP architecture to transform call transcripts to PRDs to actionable Linear issues and track project deliverables.
Agents API - Linear Tickets Demo
Financial analyst.
A financial advisory agent constructed with our Agents API, orchestrating multiple MCP servers to source financial metrics, compile insights, and archive results securely.
Agents API - Financial Analyst Demo
Travel assistant.
A powerful AI travel assistant that helps users plan their trips, book accommodations, and manage travel needs.
Agents API - Travel Assistant Demo
Nutrition assistant.
An AI-powered food diet companion designed to help users establish goals, log meals, receive personalized food suggestions, track their daily achievements, and discover dining options that align with their nutritional targets.
Create an agent with built-in connectors and MCP tools.
Each agent can be equipped with powerful built-in connectors, which are tools that are deployed and ready for Agents to call on demand, and MCP tools:
The Agents API can use the code execution connector, empowering developers to create agents that execute Python code in a secure sandboxed environment. This enables agents to tackle various tasks, including mathematical calculations, data visualization, and scientific computing.
The image generation connector, powered by Black Forest Lab FLUX1.1 [pro] Ultra, enables agents to create images for diverse applications, such as generating visual aids for educational content, creating custom graphics for marketing materials, or producing artistic images.
This built-in connector tool enables agents to access documents from Mistral Cloud, enhancing agents’ knowledge by leveraging user-uploaded document content.
The Agents API offers web search as a connector, enabling developers to combine Mistral models with up-to-date information from web search, enhancing performance and response accuracy.
SimpleQA Accuracy (Higher is better)
The Agents API SDK can also leverage tools built on the Model Context Protocol (MCP), which provides a flexible interface for agents to access real-world context, including APIs, databases, user data, documents, and other dynamic resources.
Memory and context with stateful conversations.
The Agents API provides robust conversation management through a flexible and stateful conversation system. Each conversation retains its context, allowing for seamless interactions over time.
There are two ways to start a conversation:
- With an Agent: Create a conversation with a specific agent_id to leverage its capabilities.
- Direct Access: Start a conversation by specifying the model and completion parameters for quick access.
Each conversation maintains a structured history through entries, ensuring that context is preserved.
Developers can view past conversations and continue or initiate new conversation paths as needed.
The API also supports streaming outputs, allowing for real-time updates and interactions.
Agent orchestration.
The true power of our Agents API lies in its ability to orchestrate multiple agents to solve complex problems. Through dynamic orchestration, agents can be added or removed from a conversation as needed, contributing unique capabilities.
To build a workflow, create all necessary agents, each with specific tools and models.
Once agents are created, define which agents can hand off tasks. This collaborative approach allows for efficient problem-solving, unlocking powerful possibilities for real-world applications.
Get started.
To get started, check out our docs, create your first agent, and start building!