Look at me, I'm Mr Meeseeks.
Meeseeks is an innovative AI assistant built on a multi-agent large language model (LLM) architecture. It tackles complex problems by breaking them down into atomic, reproducible tasks, each handled by autonomous agents powered by LLMs. This approach, combined with semantic caching, significantly enhances efficiency and reduces LLM calls. It is also tested to work with OpenAI-compatible endpoints [*]. Meeseeks can also call different endpoints for different tools.
Legends (Expand to View)
| Completed | In-Progress | Planned | Scoping |
|---|---|---|---|
| ✅ | 🚧 | 📅 | 🧐 |
Note
Visit Features - Wiki for detailed information on tools and integration capabilities.
| Answer questions and interpret sensor information | Control devices and entities |
|---|---|
 |
 |
- (✅) LangFuse integrations to accurate log and monitor chains.
- (✅) Use natural language to interact with integrations and tools.
- (✅) Simple REST API interface for 3rd party tools to interface with Meeseeks.
- (✅) Handles complex user queries by breaking them into actionable steps, executing these steps, and then summarizing on the results.
- (✅) Custom Home Assistant Conversation Integration to allow voice assistance via HA Assist.
- (✅) A chat Interface using
streamlitthat shows the action plan, user types, and response from the LLM.
Optional feature that users can choose to install to further optimize their experience.
- (📅)
QualityUse CRITIC reflection framework to reflect on a response to a task/query using external tools via[^]. - (🚧)
PrivacyIntegrate with microsoft/presidio for customizable PII de-identification.
- (✅) Home Assistant
- (🚧) Google Calendar
- (🚧) Google Search, Search recent ArXiv papers and summaries, Yahoo Finance, Yelp
- (🧐) Android Debugging Shell
Important
For Docker or manual installation, running, and configuring Meeseeks, visit Installation - Wiki.
We welcome contributions from the community to help improve Meeseeks. Whether you want to fix a bug, add a new feature, or integrate a new tool, your contributions are highly appreciated.
To contribute to Meeseeks, please follow these steps:
- Fork the repository and clone it to your local machine.
- Create a new branch for your contribution.
- Make your changes, commit your changes and push them to your forked repository.
- Open a pull request to the main repository, describing your changes and the problem they solve.
If you encounter any bugs or have ideas for new features, please open an issue on our issue tracker. We appreciate detailed bug reports that include steps to reproduce the issue and any relevant error messages.
Thank you for considering contributing to Meeseeks! Let's build cool stuff!