Repository files navigation

TypeAgent issample code that explores an architecture for usingTypeChat to build apersonal agent with anatural language interface.

TypeAgent uses TypeChat to build a set of application agents thattake actions. Agents define actions using TypeChat schemas.

The TypeAgent repo contains the personal agent and example application agents, along with internal packages used to build them.

• Application agents with natural language interfaces:

  • Music Player
  • Chat
  • Browser
  • VS Code
  • List Management
  • Calendar
  • Email
  • Desktop

• Agent Dispatcher

  Explores applying TypeChat to route user requests to agents whose typed contract best matches user intent. Main component of the personal agent.

• Agent Cache

  Explores how TypeChat translations from user intent to actions can be cached, minimizing the need to go the LLM.

• Agent Shell

  An Electron application for interacting with multiple registered agents using a single unified user interface. Agent Shell includes:

  • Integrated chat experience with voice support
  • Dispatcher that dispatches to registered agents
  • Structured memory
  • Structured RAG

Storage, registration, chat, memory and other state maintained by examples istypically storedlocally inyour user folder on your development machine. State is typically saved as ordinary text or JSON files in sub-folders below your user folder.

Example agents that use the Microsoft Graph or similar external services may store state in those services.

• TypeAgent is sample code shared to encourage the exploration of natural language agent architectures using TypeChat.
• Sample agents are not intended to be implemented in real-world settings without further testing/validation.

TypeAgent is early stage sample code over TypeChat. TypeAgent is not a framework. All code in this repo is intended for building our own example apps and agents only.

• TypeAgent is inactive development with frequent updates and refactoring.
• TypeAgent has been tested with Azure Open AI services on developer's own machines only.
• TypeAgent is currently tested in English. Performance may vary in other languages.
• TypeAgent relies onTypeChat, which uses schema to validate LLM responses. An agent's validity therefore depends on how wellits schema represents the user intents and LLM responsesfor its domains.
• You are responsible for supplying anyAPI keys for services used by examples.

TypeAgent is written in TypeScript and relies on TypeChat. To understand how TypeAgent examples work, we recommend getting comfortable with TypeChat andTypeChat examples first.

The main entry point to explore TypeAgent is theAgent Shell example.

Follow these quick starts for step-by-step instructions to quickly setup tools and environments from scratch to build, run and develop.

• Windows
• WSL2
• Linux (Ubuntu/Debian)
• MacOS (coming soon)

See theinstructions in the TypeScript codedirectory for more detailed setup instructions.

For developer that are interested develop custom agents to show up in ourAgent Shell example and explore using theAgent Dispatcher to route action to the custom agents,Agent Shell example allow additional agent to be installed/registered to extent functionality. TheEcho agenttutorial is a starting point to create a plugin agent, andAgent SDK provides the details of the interface betweenAgent Dispatcher and the agent.

For developer who wants to modify TypeAgent and contribute to our repo.

Microsoft TypeAgent Repo is a mono-repo, with components organized with the following root folders based on language used.

• ts TypeScript code (Readme)
• python Python code (Readme)
• dotnet Dotnet (C#) code (Readme)

This project welcomes contributions and suggestions. Most contributions require you toagree to a Contributor License Agreement (CLA) declaring that you have the right to,and actually do, grant us the rights to use your contribution. For details, visithttps://cla.microsoft.com.

When you submit a pull request, a CLA-bot will automatically determine whether you needto provide a CLA and decorate the PR appropriately (e.g., label, comment). Simply follow theinstructions provided by the bot. You will only need to do this once across all repositories using our CLA.

This project has adopted theMicrosoft Open Source Code of Conduct.For more information see theCode of Conduct FAQ orcontactopencode@microsoft.com with any additional questions or comments.

This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsofttrademarks or logos is subject to and must followMicrosoft's Trademark & Brand Guidelines.Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship.Any use of third-party trademarks or logos are subject to those third-party's policies.